diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..4c2f482725cb3f123aa683b6f0f789ded237933e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +images/T5_model_diagram.jpg filter=lfs diff=lfs merge=lfs -text diff --git a/.streamlit/config.toml b/.streamlit/config.toml new file mode 100644 index 0000000000000000000000000000000000000000..1351925fe878f35a9e31ac01757b8a4853757090 --- /dev/null +++ b/.streamlit/config.toml @@ -0,0 +1,3 @@ +[theme] +base="light" +primaryColor="#29B4E8" diff --git a/Demo.py b/Demo.py new file mode 100644 index 0000000000000000000000000000000000000000..e6e892313fa23ac1fd9655d736e2cd3ac03d557e --- /dev/null +++ b/Demo.py @@ -0,0 +1,163 @@ +import streamlit as st +import sparknlp +import os +import pandas as pd + +from sparknlp.base import * +from sparknlp.annotator import * +from pyspark.ml import Pipeline +from sparknlp.pretrained import PretrainedPipeline + +# Page Configuration +st.set_page_config( + layout="wide", + initial_sidebar_state="auto" +) + +# Custom CSS for Styling +st.markdown(""" + +""", unsafe_allow_html=True) + +# Initialize Spark Session +@st.cache_resource +def start_spark_session(): + return sparknlp.start() + +# Create NLP Pipeline +@st.cache_resource +def build_nlp_pipeline(model_name, task): + document_assembler = DocumentAssembler()\ + .setInputCol("text")\ + .setOutputCol("document") + + t5_transformer = T5Transformer() \ + .pretrained(model_name, 'en') \ + .setTask(task)\ + .setInputCols(["document"]) \ + .setOutputCol("output") + + pipeline = Pipeline().setStages([document_assembler, t5_transformer]) + return pipeline + +# Apply Pipeline to Text Data +def process_text(pipeline, text): + df = spark.createDataFrame([[text]]).toDF("text") + result = pipeline.fit(df).transform(df) + return result.select('output.result').collect() + +# Model and Task Information +model_info = [ + { + "model_name": "t5_small", + "title": "Multi-Task NLP Model", + "description": "The T5 model performs 18 different NLP tasks including summarization, question answering, and grammatical correctness detection." + }, + { + "model_name": "t5_base", + "title": "Multi-Task NLP Model", + "description": "A larger variant of the T5 model, capable of performing a variety of NLP tasks with improved accuracy." + }, + { + "model_name": "google_t5_small_ssm_nq", + "title": "Question Answering Model", + "description": "This model is fine-tuned for answering questions based on the Natural Questions dataset, leveraging pre-training on large text corpora." + } +] + +task_descriptions = { + 'Sentence Classification - cola': "Classify if a sentence is grammatically correct.", + 'Natural Language Inference - rte': "The RTE task is defined as recognizing, given two text fragments, whether the meaning of one text can be inferred (entailed) from the other or not.", + 'Natural Language Inference - mnli': "Classify for a hypothesis and premise whether they contradict or contradict each other or neither of both (3 class).", + 'Natural Language Inference - qnli': "Classify whether the answer to a question can be deducted from an answer candidate.", + 'Natural Language Inference - cb': "Classify for a premise and a hypothesis whether they contradict each other or not (binary).", + 'Coreference Resolution - mrpc': "Classify whether a pair of sentences is a re-phrasing of each other (semantically equivalent).", + 'Coreference Resolution - qqp': "Classify whether a pair of questions is a re-phrasing of each other (semantically equivalent).", + 'Sentiment Analysis - sst2': "Classify the sentiment of a sentence as positive or negative.", + 'Sentiment Analysis - stsb': "Measures how similar two sentences are on a scale from 0 to 5", + 'Question Answering - copa': "Classify for a question, premise, and 2 choices which choice the correct choice is (binary).", + 'Question Answering - multirc': "Classify for a question, a paragraph of text, and an answer candidate, if the answer is correct (binary).", + 'Question Answering - squad': "Answer a question for a given context.", + 'Word Sense Disambiguation - wic': "Classify for a pair of sentences and a disambiguous word if the word has the same meaning in both sentences.", + 'Text - summarization': "Summarize text into a shorter representation.", + 'Translation - wmt1': "This model is used to translate one language to the other language. Example: Translate English to German.", + 'Translation - wmt2': "This model is used to translate one language to the other language. Example: Translate English to French.", + 'Translation - wmt3': "This model is used to translate one language to the other language. Example: Translate English to Romanian." +} + +# Sidebar: Task and Model Selection +selected_task = st.sidebar.selectbox("Choose an NLP Task", list(task_descriptions.keys())) +task_for_pipeline = f"{selected_task.split(' - ')[-1]}:" + +available_models = ['google_t5_small_ssm_nq'] if "Question Answering" in selected_task else ['t5_base', 't5_small'] +selected_model = st.sidebar.selectbox("Choose a Model", available_models) + +# Get Model Info +model_details = next((info for info in model_info if info['model_name'] == selected_model), None) +app_title = model_details['title'] if model_details else "Unknown Model" +app_description = model_details['description'] if model_details else "No description available." + +# Display Model Info +st.markdown(f'
{app_title}
', unsafe_allow_html=True) +st.markdown(f'

{app_description}

', unsafe_allow_html=True) +st.subheader(task_descriptions[selected_task]) + +# Load Example Texts +example_folder = f"inputs/{selected_task}/{selected_model}" +example_texts = [ + line.strip() + for file in os.listdir(example_folder) + if file.endswith('.txt') + for line in open(os.path.join(example_folder, file), 'r', encoding='utf-8') +] + +# User Input: Select or Enter Text +selected_example = st.selectbox("Select an Example", example_texts) +custom_input = st.text_input("Or enter your own text:") + +text_to_process = custom_input if custom_input else selected_example + +# Display Selected Text +st.subheader('Selected Text') +st.markdown(f'
{text_to_process}
', unsafe_allow_html=True) + +# Sidebar: Reference Notebook +st.sidebar.markdown('Reference notebook:') +st.sidebar.markdown(""" + + Open In Colab + +""", unsafe_allow_html=True) + +# Special Cases for Translation Tasks +task_for_pipeline = { + 'wmt1:': 'translate English to German:', + 'wmt2:': 'translate English to French:', + 'wmt3:': 'translate English to Romanian:' +}.get(task_for_pipeline, task_for_pipeline) + +# Initialize Spark, Build Pipeline, and Process Text +spark = start_spark_session() +nlp_pipeline = build_nlp_pipeline(selected_model, task_for_pipeline) +processed_output = process_text(nlp_pipeline, text_to_process) + +# Display Processed Output +st.subheader("Processed Output") +output_text = "".join(processed_output[0][0]) +st.markdown(f'
{output_text}
', unsafe_allow_html=True) diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000000000000000000000000000000000000..9bfdb55fe4c4a7afeedff8f137e4b25c06115433 --- /dev/null +++ b/Dockerfile @@ -0,0 +1,70 @@ +# Download base image ubuntu 18.04 +FROM ubuntu:18.04 + +# Set environment variables +ENV NB_USER jovyan +ENV NB_UID 1000 +ENV HOME /home/${NB_USER} + +# Install required packages +RUN apt-get update && apt-get install -y \ + tar \ + wget \ + bash \ + rsync \ + gcc \ + libfreetype6-dev \ + libhdf5-serial-dev \ + libpng-dev \ + libzmq3-dev \ + python3 \ + python3-dev \ + python3-pip \ + unzip \ + pkg-config \ + software-properties-common \ + graphviz \ + openjdk-8-jdk \ + ant \ + ca-certificates-java \ + && apt-get clean \ + && update-ca-certificates -f; + +# Install Python 3.8 and pip +RUN add-apt-repository ppa:deadsnakes/ppa \ + && apt-get update \ + && apt-get install -y python3.8 python3-pip \ + && apt-get clean; + +# Set up JAVA_HOME +ENV JAVA_HOME /usr/lib/jvm/java-8-openjdk-amd64/ +RUN mkdir -p ${HOME} \ + && echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> ${HOME}/.bashrc \ + && chown -R ${NB_UID}:${NB_UID} ${HOME} + +# Create a new user named "jovyan" with user ID 1000 +RUN useradd -m -u ${NB_UID} ${NB_USER} + +# Switch to the "jovyan" user +USER ${NB_USER} + +# Set home and path variables for the user +ENV HOME=/home/${NB_USER} \ + PATH=/home/${NB_USER}/.local/bin:$PATH + +# Set the working directory to the user's home directory +WORKDIR ${HOME} + +# Upgrade pip and install Python dependencies +RUN python3.8 -m pip install --upgrade pip +COPY requirements.txt /tmp/requirements.txt +RUN python3.8 -m pip install -r /tmp/requirements.txt + +# Copy the application code into the container at /home/jovyan +COPY --chown=${NB_USER}:${NB_USER} . ${HOME} + +# Expose port for Streamlit +EXPOSE 7860 + +# Define the entry point for the container +ENTRYPOINT ["streamlit", "run", "Demo.py", "--server.port=7860", "--server.address=0.0.0.0"] \ No newline at end of file diff --git a/images/T5_model_diagram.jpg b/images/T5_model_diagram.jpg new file mode 100644 index 0000000000000000000000000000000000000000..2193a33ba377d71f5e4018b63586ef13f3d3b4f0 --- /dev/null +++ b/images/T5_model_diagram.jpg @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdc448c0c71610fa26d4063fd82edb1b6e879d3cb0e17fd2e8d29565a1ccbc4 +size 3152264 diff --git a/inputs/Coreference Resolution - mrpc/t5_base/Example1.txt b/inputs/Coreference Resolution - mrpc/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..b7be62ba15abec199bf3c6db9bdaaa038595836d --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_base/Example1.txt @@ -0,0 +1,2 @@ +We acted because we saw the existing evidence in a new light, through the prism of our experienc... +We acted because we saw the existing evidence in a new light, through the prism of our experience on 11 September Rumsfeld said. sentence2: Rather, the US acted because the administration saw existing evidence in a new light, through the prism of our experience on September 11. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_base/Example2.txt b/inputs/Coreference Resolution - mrpc/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..459d5148c2593ce9b5b4c27ab91b66f36b2a1efc --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_base/Example2.txt @@ -0,0 +1,2 @@ +I like to eat peanut butter for breakfast. +I like to eat peanut butter for breakfast. sentence2: I like to play football. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_base/Example3.txt b/inputs/Coreference Resolution - mrpc/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..def2b89182fd230fb2133537e0ef810856c981a6 --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Charles O. Prince, 53, was named as Mr. Weill’s successor. +Charles O. Prince, 53, was named as Mr. Weill’s successor. sentence2: Mr. Weill’s longtime confidant, Charles O. Prince, 53, was named as his successor. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_base/Example4.txt b/inputs/Coreference Resolution - mrpc/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..a2c9b2e1df6136ece1045e56550942272d25f176 --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_base/Example4.txt @@ -0,0 +1,2 @@ +The euro rose above US$1.18, the highest price since its January ... +The euro rose above US$1.18, the highest price since its January 1999 launch. sentence2: The euro rose above $1.18 the high-est level since its launch in January 1999. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_base/Example5.txt b/inputs/Coreference Resolution - mrpc/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..b6ecbab881ceb7bf7fcb30586fa34941367e85b5 --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_base/Example5.txt @@ -0,0 +1,2 @@ +However, without a carefully con-trolled study, there was ... +However, without a carefully con-trolled study, there was little clear proof that the operation ac-tually improves people’s lives. sentence2: But without a carefully controlled study, there was little clear proof that the operation improves people’s lives. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_small/Example1.txt b/inputs/Coreference Resolution - mrpc/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..ebef057b4d34dae67440c36bdf022fd2bf4aa49f --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_small/Example1.txt @@ -0,0 +1,2 @@ +We acted because we saw the existing evidence in a new light, through the prism of our experienc... +We acted because we saw the existing evidence in a new light, through the prism of our experience on 11 September" Rumsfeld said. sentence2: Rather, the US acted because the administration saw "existing evidence in a new light, through the prism of our experience on September 11". \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_small/Example2.txt b/inputs/Coreference Resolution - mrpc/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..5bc78905d5e6c276df329e0b91f8020ad920ce5a --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_small/Example2.txt @@ -0,0 +1,2 @@ +I like to eat peanutbutter for breakfast. +I like to eat peanutbutter for breakfast. sentence2: I like to play football. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_small/Example3.txt b/inputs/Coreference Resolution - mrpc/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..def2b89182fd230fb2133537e0ef810856c981a6 --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Charles O. Prince, 53, was named as Mr. Weill’s successor. +Charles O. Prince, 53, was named as Mr. Weill’s successor. sentence2: Mr. Weill’s longtime confidant, Charles O. Prince, 53, was named as his successor. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_small/Example4.txt b/inputs/Coreference Resolution - mrpc/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..a2c9b2e1df6136ece1045e56550942272d25f176 --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_small/Example4.txt @@ -0,0 +1,2 @@ +The euro rose above US$1.18, the highest price since its January ... +The euro rose above US$1.18, the highest price since its January 1999 launch. sentence2: The euro rose above $1.18 the high-est level since its launch in January 1999. \ No newline at end of file diff --git a/inputs/Coreference Resolution - mrpc/t5_small/Example5.txt b/inputs/Coreference Resolution - mrpc/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..b6ecbab881ceb7bf7fcb30586fa34941367e85b5 --- /dev/null +++ b/inputs/Coreference Resolution - mrpc/t5_small/Example5.txt @@ -0,0 +1,2 @@ +However, without a carefully con-trolled study, there was ... +However, without a carefully con-trolled study, there was little clear proof that the operation ac-tually improves people’s lives. sentence2: But without a carefully controlled study, there was little clear proof that the operation improves people’s lives. \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_base/Example1.txt b/inputs/Coreference Resolution - qqp/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..f509ebd576e1370f9d5aa7f4b063cb636bcd3743 --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_base/Example1.txt @@ -0,0 +1,2 @@ +question1: What attributes would have made you highly desirable in ancient Rome? +question1: What attributes would have made you highly desirable in ancient Rome? question2: How I GET OPPERTINUTY TO JOIN IT COMPANY AS A FRESHER?' \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_base/Example2.txt b/inputs/Coreference Resolution - qqp/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..447ee956a6ecdc0143a529ed94895dec66795bfe --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_base/Example2.txt @@ -0,0 +1,2 @@ +question1: What was it like in Ancient rome? +question1: What was it like in Ancient rome? question2: What was Ancient rome like? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_base/Example3.txt b/inputs/Coreference Resolution - qqp/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..5fb06d9c91125a5e6151a402eca72b3c46f2d338 --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_base/Example3.txt @@ -0,0 +1,2 @@ +question1: How can I install Windows software or games? +question1: How can I install Windows software or games? question2: I cannot install Windows. How to install it? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_base/Example4.txt b/inputs/Coreference Resolution - qqp/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..c28468bd8ffb47989442b34a98fc19062839b72d --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_base/Example4.txt @@ -0,0 +1,2 @@ +question1: Could you live without the internet? +question1: Could you live without the internet? question2: Internet is not available for a few days. Could you manage without it? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_base/Example5.txt b/inputs/Coreference Resolution - qqp/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..6ad67498a9f0524ceb1ec840a14b3e0daea9084d --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_base/Example5.txt @@ -0,0 +1,2 @@ +question1: What is the best thing that happened to you during the past week? +question1: What is the best thing that happened to you during the past week? question2: What is the best thing that happened to you during the past year? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_small/Example1.txt b/inputs/Coreference Resolution - qqp/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..f509ebd576e1370f9d5aa7f4b063cb636bcd3743 --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_small/Example1.txt @@ -0,0 +1,2 @@ +question1: What attributes would have made you highly desirable in ancient Rome? +question1: What attributes would have made you highly desirable in ancient Rome? question2: How I GET OPPERTINUTY TO JOIN IT COMPANY AS A FRESHER?' \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_small/Example2.txt b/inputs/Coreference Resolution - qqp/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..447ee956a6ecdc0143a529ed94895dec66795bfe --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_small/Example2.txt @@ -0,0 +1,2 @@ +question1: What was it like in Ancient rome? +question1: What was it like in Ancient rome? question2: What was Ancient rome like? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_small/Example3.txt b/inputs/Coreference Resolution - qqp/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..5fb06d9c91125a5e6151a402eca72b3c46f2d338 --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_small/Example3.txt @@ -0,0 +1,2 @@ +question1: How can I install Windows software or games? +question1: How can I install Windows software or games? question2: I cannot install Windows. How to install it? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_small/Example4.txt b/inputs/Coreference Resolution - qqp/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..c28468bd8ffb47989442b34a98fc19062839b72d --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_small/Example4.txt @@ -0,0 +1,2 @@ +question1: Could you live without the internet? +question1: Could you live without the internet? question2: Internet is not available for a few days. Could you manage without it? \ No newline at end of file diff --git a/inputs/Coreference Resolution - qqp/t5_small/Example5.txt b/inputs/Coreference Resolution - qqp/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..6ad67498a9f0524ceb1ec840a14b3e0daea9084d --- /dev/null +++ b/inputs/Coreference Resolution - qqp/t5_small/Example5.txt @@ -0,0 +1,2 @@ +question1: What is the best thing that happened to you during the past week? +question1: What is the best thing that happened to you during the past week? question2: What is the best thing that happened to you during the past year? \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_base/Example1.txt b/inputs/Natural Language Inference - cb/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..a7113d129ba9299c74f4bf9e2cab365a4e00c0a6 --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_base/Example1.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. premise: Johnny is a poor man. \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_base/Example2.txt b/inputs/Natural Language Inference - cb/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..bf972d66e0830a74d50ab0a8ff31c13dab019dbe --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_base/Example2.txt @@ -0,0 +1,2 @@ +It rained in England the last 4 weeks. premise: It was snowing in New Yor... +It rained in England the last 4 weeks. premise: It was snowing in New York last week. \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_base/Example3.txt b/inputs/Natural Language Inference - cb/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..cac565d32021655e2ac44d0cc528e28aefb1bbe4 --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Man in a black suit, white shirt and black bow tie playing an instrument with ... +Man in a black suit, white shirt and black bow tie playing an instrument with the rest of his symphony surrounding him. premise:Nobody has a suit \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_base/Example4.txt b/inputs/Natural Language Inference - cb/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..dcb19401f903969058f56ca49ea6305aefbd229b --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_base/Example4.txt @@ -0,0 +1,2 @@ +At 8:34, the Boston Center controller received a third, transmission from ... +At 8:34, the Boston Center controller received a third, transmission from American 11. premise:The Boston Center controller got a third transmission from American 11. \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_base/Example5.txt b/inputs/Natural Language Inference - cb/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..87405b15a857ac23c3b7d1ae31f75f3e5fe97b6e --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_base/Example5.txt @@ -0,0 +1,2 @@ +Cats with long hair shed all over the house so you should not get a long-.... +Cats with long hair shed all over the house so you should not get a long-haired cat premise: Long hair cats are good \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_small/Example1.txt b/inputs/Natural Language Inference - cb/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..a7113d129ba9299c74f4bf9e2cab365a4e00c0a6 --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_small/Example1.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. premise: Johnny is a poor man. \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_small/Example2.txt b/inputs/Natural Language Inference - cb/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..bf972d66e0830a74d50ab0a8ff31c13dab019dbe --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_small/Example2.txt @@ -0,0 +1,2 @@ +It rained in England the last 4 weeks. premise: It was snowing in New Yor... +It rained in England the last 4 weeks. premise: It was snowing in New York last week. \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_small/Example3.txt b/inputs/Natural Language Inference - cb/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..cac565d32021655e2ac44d0cc528e28aefb1bbe4 --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Man in a black suit, white shirt and black bow tie playing an instrument with ... +Man in a black suit, white shirt and black bow tie playing an instrument with the rest of his symphony surrounding him. premise:Nobody has a suit \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_small/Example4.txt b/inputs/Natural Language Inference - cb/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..dcb19401f903969058f56ca49ea6305aefbd229b --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_small/Example4.txt @@ -0,0 +1,2 @@ +At 8:34, the Boston Center controller received a third, transmission from ... +At 8:34, the Boston Center controller received a third, transmission from American 11. premise:The Boston Center controller got a third transmission from American 11. \ No newline at end of file diff --git a/inputs/Natural Language Inference - cb/t5_small/Example5.txt b/inputs/Natural Language Inference - cb/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..87405b15a857ac23c3b7d1ae31f75f3e5fe97b6e --- /dev/null +++ b/inputs/Natural Language Inference - cb/t5_small/Example5.txt @@ -0,0 +1,2 @@ +Cats with long hair shed all over the house so you should not get a long-.... +Cats with long hair shed all over the house so you should not get a long-haired cat premise: Long hair cats are good \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_base/Example1.txt b/inputs/Natural Language Inference - mnli/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..9ef05dfb04e5b5fe1f1a8c734f4d9ec9f2783719 --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_base/Example1.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. premise: Johnny is a poor man. \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_base/Example2.txt b/inputs/Natural Language Inference - mnli/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..8f1053dc11ae8d5a2a552513e453fb2c8886fcfb --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_base/Example2.txt @@ -0,0 +1,2 @@ +It rained in England the last 4 weeks. +It rained in England the last 4 weeks. premise: It was snowing in New York last week. \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_base/Example3.txt b/inputs/Natural Language Inference - mnli/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..cac565d32021655e2ac44d0cc528e28aefb1bbe4 --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Man in a black suit, white shirt and black bow tie playing an instrument with ... +Man in a black suit, white shirt and black bow tie playing an instrument with the rest of his symphony surrounding him. premise:Nobody has a suit \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_base/Example4.txt b/inputs/Natural Language Inference - mnli/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..dcb19401f903969058f56ca49ea6305aefbd229b --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_base/Example4.txt @@ -0,0 +1,2 @@ +At 8:34, the Boston Center controller received a third, transmission from ... +At 8:34, the Boston Center controller received a third, transmission from American 11. premise:The Boston Center controller got a third transmission from American 11. \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_base/Example5.txt b/inputs/Natural Language Inference - mnli/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..87405b15a857ac23c3b7d1ae31f75f3e5fe97b6e --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_base/Example5.txt @@ -0,0 +1,2 @@ +Cats with long hair shed all over the house so you should not get a long-.... +Cats with long hair shed all over the house so you should not get a long-haired cat premise: Long hair cats are good \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_small/Example1.txt b/inputs/Natural Language Inference - mnli/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..a7113d129ba9299c74f4bf9e2cab365a4e00c0a6 --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_small/Example1.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. premise: Johnny is a poor man. \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_small/Example2.txt b/inputs/Natural Language Inference - mnli/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..bf972d66e0830a74d50ab0a8ff31c13dab019dbe --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_small/Example2.txt @@ -0,0 +1,2 @@ +It rained in England the last 4 weeks. premise: It was snowing in New Yor... +It rained in England the last 4 weeks. premise: It was snowing in New York last week. \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_small/Example3.txt b/inputs/Natural Language Inference - mnli/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..cac565d32021655e2ac44d0cc528e28aefb1bbe4 --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Man in a black suit, white shirt and black bow tie playing an instrument with ... +Man in a black suit, white shirt and black bow tie playing an instrument with the rest of his symphony surrounding him. premise:Nobody has a suit \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_small/Example4.txt b/inputs/Natural Language Inference - mnli/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..dcb19401f903969058f56ca49ea6305aefbd229b --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_small/Example4.txt @@ -0,0 +1,2 @@ +At 8:34, the Boston Center controller received a third, transmission from ... +At 8:34, the Boston Center controller received a third, transmission from American 11. premise:The Boston Center controller got a third transmission from American 11. \ No newline at end of file diff --git a/inputs/Natural Language Inference - mnli/t5_small/Example5.txt b/inputs/Natural Language Inference - mnli/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..87405b15a857ac23c3b7d1ae31f75f3e5fe97b6e --- /dev/null +++ b/inputs/Natural Language Inference - mnli/t5_small/Example5.txt @@ -0,0 +1,2 @@ +Cats with long hair shed all over the house so you should not get a long-.... +Cats with long hair shed all over the house so you should not get a long-haired cat premise: Long hair cats are good \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_base/Example1.txt b/inputs/Natural Language Inference - qnli/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..fb1da7b62f82bfd08e60b849c22ae00986560891 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_base/Example1.txt @@ -0,0 +1,2 @@ +question: Where did Jebe die? sentence: Ghenkis Khan recalled Subtai back... +question: Where did Jebe die? sentence: Ghenkis Khan recalled Subtai back to Mongolia soon afterward, and Jebe died on the road back to Samarkand \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_base/Example2.txt b/inputs/Natural Language Inference - qnli/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ada7c19777638f8e9f893e3adafcd04f5836b6a --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_base/Example2.txt @@ -0,0 +1,2 @@ +question: What does Steve like to eat? sentence: Steve watches TV all day. +question: What does Steve like to eat? sentence: Steve watches TV all day. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_base/Example3.txt b/inputs/Natural Language Inference - qnli/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..c21ac297803eb9c3b2cbe285bb3d19331f3f42c3 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_base/Example3.txt @@ -0,0 +1,2 @@ +question: What space station supported three manned missions in 1973–1974? +question: What space station supported three manned missions in 1973–1974? sentence: Apollo/Saturn vehicles were also used for an Apollo Applications Program, which consisted of Skylab, a space station that supported three manned missions in 1973–74, and the Apollo–Soyuz Test Project, a joint Earth orbit mission with the Soviet Union in 1975. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_base/Example4.txt b/inputs/Natural Language Inference - qnli/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..cb530d2a61df6341bc32821a359372df1370f3e0 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_base/Example4.txt @@ -0,0 +1,2 @@ +question: When did Beyonce start becoming popular? +question: When did Beyonce start becoming popular? sentence: Beyoncé was born and raised in Houston, Texas, she performed in various singing and dancing competitions as a child, and rose to fame in the late 1990s as lead singer of R&B girl-group Destiny's Child. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_base/Example5.txt b/inputs/Natural Language Inference - qnli/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..639b96a5a878998767d417c8ae87be7f2cef2b68 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_base/Example5.txt @@ -0,0 +1,2 @@ +question: Which NFL team represented the AFC at Super Bowl 50? +question: Which NFL team represented the AFC at Super Bowl 50? sentence: Super Bowl 50 was an American football game to determine the champion of the National Football League (NFL) for the 2015 season. The American Football Conference (AFC) champion Denver Broncos defeated the National Football Conference (NFC) champion Carolina Panthers 24–10 to earn their third Super Bowl title. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_small/Example1.txt b/inputs/Natural Language Inference - qnli/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..fb1da7b62f82bfd08e60b849c22ae00986560891 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_small/Example1.txt @@ -0,0 +1,2 @@ +question: Where did Jebe die? sentence: Ghenkis Khan recalled Subtai back... +question: Where did Jebe die? sentence: Ghenkis Khan recalled Subtai back to Mongolia soon afterward, and Jebe died on the road back to Samarkand \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_small/Example2.txt b/inputs/Natural Language Inference - qnli/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ada7c19777638f8e9f893e3adafcd04f5836b6a --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_small/Example2.txt @@ -0,0 +1,2 @@ +question: What does Steve like to eat? sentence: Steve watches TV all day. +question: What does Steve like to eat? sentence: Steve watches TV all day. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_small/Example3.txt b/inputs/Natural Language Inference - qnli/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..c21ac297803eb9c3b2cbe285bb3d19331f3f42c3 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_small/Example3.txt @@ -0,0 +1,2 @@ +question: What space station supported three manned missions in 1973–1974? +question: What space station supported three manned missions in 1973–1974? sentence: Apollo/Saturn vehicles were also used for an Apollo Applications Program, which consisted of Skylab, a space station that supported three manned missions in 1973–74, and the Apollo–Soyuz Test Project, a joint Earth orbit mission with the Soviet Union in 1975. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_small/Example4.txt b/inputs/Natural Language Inference - qnli/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..cb530d2a61df6341bc32821a359372df1370f3e0 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_small/Example4.txt @@ -0,0 +1,2 @@ +question: When did Beyonce start becoming popular? +question: When did Beyonce start becoming popular? sentence: Beyoncé was born and raised in Houston, Texas, she performed in various singing and dancing competitions as a child, and rose to fame in the late 1990s as lead singer of R&B girl-group Destiny's Child. \ No newline at end of file diff --git a/inputs/Natural Language Inference - qnli/t5_small/Example5.txt b/inputs/Natural Language Inference - qnli/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..639b96a5a878998767d417c8ae87be7f2cef2b68 --- /dev/null +++ b/inputs/Natural Language Inference - qnli/t5_small/Example5.txt @@ -0,0 +1,2 @@ +question: Which NFL team represented the AFC at Super Bowl 50? +question: Which NFL team represented the AFC at Super Bowl 50? sentence: Super Bowl 50 was an American football game to determine the champion of the National Football League (NFL) for the 2015 season. The American Football Conference (AFC) champion Denver Broncos defeated the National Football Conference (NFC) champion Carolina Panthers 24–10 to earn their third Super Bowl title. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_base/Example1.txt b/inputs/Natural Language Inference - rte/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..78122ff59fcc6b287729332024ea0b86cacae5ee --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_base/Example1.txt @@ -0,0 +1,2 @@ +Kessler’s team conducted 60,643 interviews with adults in 14 countries. S... +Kessler’s team conducted 60,643 interviews with adults in 14 countries. Sentence 2: Kessler’s team interviewed more than 60,000 adults in 14 countries \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_base/Example2.txt b/inputs/Natural Language Inference - rte/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..956938a18449fd4fe607255e933342594d2b6bb4 --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Peter loves New York, it is his favorite city. +Peter loves New York, it is his favorite city. Sentence 2: Peter loves new York. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_base/Example3.txt b/inputs/Natural Language Inference - rte/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..7092e3086100b1dd7d724babc5a5a4c61b7b8ee7 --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. Sentence 2: Johnny is a millionare. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_base/Example4.txt b/inputs/Natural Language Inference - rte/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..f31946fb1d30310d2b9e79df16e4a0fa86f374b9 --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_base/Example4.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. Sentence 2: Johnny is a poor man. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_base/Example5.txt b/inputs/Natural Language Inference - rte/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..9c76a3502b4022d22b4325737aa1a3d529f0721f --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_base/Example5.txt @@ -0,0 +1,2 @@ +It was raining in England for the last 4 weeks. +It was raining in England for the last 4 weeks. Sentence 2: England was very dry yesterday. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_small/Example1.txt b/inputs/Natural Language Inference - rte/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..78122ff59fcc6b287729332024ea0b86cacae5ee --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_small/Example1.txt @@ -0,0 +1,2 @@ +Kessler’s team conducted 60,643 interviews with adults in 14 countries. S... +Kessler’s team conducted 60,643 interviews with adults in 14 countries. Sentence 2: Kessler’s team interviewed more than 60,000 adults in 14 countries \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_small/Example2.txt b/inputs/Natural Language Inference - rte/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..2a2403768abfc9055f8316a01cc705e9eef31082 --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Peter loves New York, it is his favorite city. +Peter loves New York, it is his favorite city. Sentence 2: Peter loves new York. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_small/Example3.txt b/inputs/Natural Language Inference - rte/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b679f472ee0cf2a1976f7d5e326c0c97afedbd00 --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. Sentence 2: Johnny is a millionare. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_small/Example4.txt b/inputs/Natural Language Inference - rte/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..106f1f2ce3c4dec15583a385f75057056bb725ec --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_small/Example4.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last ... +Recent report say Johnny makes he alot of money, he earned 10 million USD each year for the last 5 years. Sentence 2: Johnny is a poor man. \ No newline at end of file diff --git a/inputs/Natural Language Inference - rte/t5_small/Example5.txt b/inputs/Natural Language Inference - rte/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..7928fdad1488fd3647ea827318172cd4aae1345f --- /dev/null +++ b/inputs/Natural Language Inference - rte/t5_small/Example5.txt @@ -0,0 +1,2 @@ +It was raining in England for the last 4 weeks. +It was raining in England for the last 4 weeks. Sentence 2: England was very dry yesterday. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_base/Example1.txt b/inputs/Question Answering - multirc/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..d260ffaeeabd3bfc48bcdf093edb8489f48f5f14 --- /dev/null +++ b/inputs/Question Answering - multirc/t5_base/Example1.txt @@ -0,0 +1,2 @@ +questions: Why was Joey surprised the morning he woke up for breakfast? +questions: Why was Joey surprised the morning he woke up for breakfast? answer: There was a T-REX in his garden. paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_base/Example2.txt b/inputs/Question Answering - multirc/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..68c8f2525fd27f7e0fd6c4d845f0b60e71ed075a --- /dev/null +++ b/inputs/Question Answering - multirc/t5_base/Example2.txt @@ -0,0 +1,2 @@ +questions: Why was Joey surprised the morning he woke up for breakfast? +questions: Why was Joey surprised the morning he woke up for breakfast? answer:There was only pie for breakfast. paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_base/Example3.txt b/inputs/Question Answering - multirc/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..20aa3f067028346667425f7906cc3132eefd43ed --- /dev/null +++ b/inputs/Question Answering - multirc/t5_base/Example3.txt @@ -0,0 +1,2 @@ +questions: Who was Joey's Cousin? +questions: Who was Joey's Cousin? answer:Jimmy paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_base/Example4.txt b/inputs/Question Answering - multirc/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..41651829209bf93f9460740393765b7185f85e83 --- /dev/null +++ b/inputs/Question Answering - multirc/t5_base/Example4.txt @@ -0,0 +1,2 @@ +questions: Who was Joey's Friend? +questions: Who was Joey's Friend? answer: Jack Rabbit paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_small/Example1.txt b/inputs/Question Answering - multirc/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..d260ffaeeabd3bfc48bcdf093edb8489f48f5f14 --- /dev/null +++ b/inputs/Question Answering - multirc/t5_small/Example1.txt @@ -0,0 +1,2 @@ +questions: Why was Joey surprised the morning he woke up for breakfast? +questions: Why was Joey surprised the morning he woke up for breakfast? answer: There was a T-REX in his garden. paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_small/Example2.txt b/inputs/Question Answering - multirc/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..68c8f2525fd27f7e0fd6c4d845f0b60e71ed075a --- /dev/null +++ b/inputs/Question Answering - multirc/t5_small/Example2.txt @@ -0,0 +1,2 @@ +questions: Why was Joey surprised the morning he woke up for breakfast? +questions: Why was Joey surprised the morning he woke up for breakfast? answer:There was only pie for breakfast. paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_small/Example3.txt b/inputs/Question Answering - multirc/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..20aa3f067028346667425f7906cc3132eefd43ed --- /dev/null +++ b/inputs/Question Answering - multirc/t5_small/Example3.txt @@ -0,0 +1,2 @@ +questions: Who was Joey's Cousin? +questions: Who was Joey's Cousin? answer:Jimmy paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - multirc/t5_small/Example4.txt b/inputs/Question Answering - multirc/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..41651829209bf93f9460740393765b7185f85e83 --- /dev/null +++ b/inputs/Question Answering - multirc/t5_small/Example4.txt @@ -0,0 +1,2 @@ +questions: Who was Joey's Friend? +questions: Who was Joey's Friend? answer: Jack Rabbit paragraph: Sent 1: Once upon a time, there was a squirrel named Joey. Sent 2: Joey loved to go outside and play with his cousin Jimmy. Sent 3: Joey and Jimmy played silly games together, and were always laughing. Sent 4: One day, Joey and Jimmy went swimming together 50 at their Aunt Julie’s pond. Sent 5: Joey woke up early in the morning to eat some food before they left. Sent 6: He couldn’t find anything to eat except for pie! Sent 7: Usually, Joey would eat cereal, fruit (a pear), or oatmeal for breakfast. Sent 8: After he ate, he and Jimmy went to the pond. Sent 9: On their way there they saw their friend Jack Rabbit. Sent 10: They dove into the water and swam for several hours. Sent 11: The sun was out, but the breeze was cold. Sent 12: Joey and Jimmy got out of the water and started walking home. Sent 13: Their fur was wet, and the breeze chilled them. Sent 14: When they got home, they dried off, and Jimmy put on his favorite purple shirt. Sent 15: Joey put on a blue shirt with red and green dots. Sent 16: The two squirrels ate some food that Joey’s mom, Jasmine, made and went off to bed. \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_base/Example1.txt b/inputs/Question Answering - copa/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..d932d7cee5cc80f618cca89d1d3c805fda9444a2 --- /dev/null +++ b/inputs/Question Answering - copa/t5_base/Example1.txt @@ -0,0 +1,2 @@ +He fell off the ladder +choice1: He fell off the ladder choice2: He climbed up the lader premise: The man lost his balance on the ladder question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_base/Example2.txt b/inputs/Question Answering - copa/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..320529aa572207aa575eaee61e5beb6179578653 --- /dev/null +++ b/inputs/Question Answering - copa/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he a lot of money, he earned 10 ... +choice1: Johnny is a rich man choice2: Johnny is a poor man premise: Recent report say Johnny makes he a lot of money, he earned 10 million USD each year for the last 5 years. question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_base/Example3.txt b/inputs/Question Answering - copa/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..587f2daff140447d7c7f699184d1f0457ab14d40 --- /dev/null +++ b/inputs/Question Answering - copa/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Man in a black suit, white shirt and black bow tie playing an instrument with the rest ... +choice1: Somebody has a suit choice2: Nobody has a suit premise: Man in a black suit, white shirt and black bow tie playing an instrument with the rest of his symphony surrounding him. question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_base/Example4.txt b/inputs/Question Answering - copa/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..4362f21b0a9439180d22203b2c5f63e15442ba60 --- /dev/null +++ b/inputs/Question Answering - copa/t5_base/Example4.txt @@ -0,0 +1,2 @@ +At 8:34, the Boston Center controller received a third, transmission from American 11 +choice1: The Boston Center controller got a fourth transmission from American 13 choice2: The Boston Center controller got a third transmission from American 11 premise: At 8:34, the Boston Center controller received a third, transmission from American 11 question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_base/Example5.txt b/inputs/Question Answering - copa/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..f8f5d8672e5a9effd04b8aa9f6d187bcab0ab62d --- /dev/null +++ b/inputs/Question Answering - copa/t5_base/Example5.txt @@ -0,0 +1,2 @@ +Cats with long hair shed all over the house so you should not get a long-haired cat +choice1: Long hair cats are bad choice2: Long hair cats are good premise: Cats with long hair shed all over the house so you should not get a long-haired cat question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_small/Example1.txt b/inputs/Question Answering - copa/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..d932d7cee5cc80f618cca89d1d3c805fda9444a2 --- /dev/null +++ b/inputs/Question Answering - copa/t5_small/Example1.txt @@ -0,0 +1,2 @@ +He fell off the ladder +choice1: He fell off the ladder choice2: He climbed up the lader premise: The man lost his balance on the ladder question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_small/Example2.txt b/inputs/Question Answering - copa/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..320529aa572207aa575eaee61e5beb6179578653 --- /dev/null +++ b/inputs/Question Answering - copa/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Recent report say Johnny makes he a lot of money, he earned 10 ... +choice1: Johnny is a rich man choice2: Johnny is a poor man premise: Recent report say Johnny makes he a lot of money, he earned 10 million USD each year for the last 5 years. question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_small/Example3.txt b/inputs/Question Answering - copa/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..587f2daff140447d7c7f699184d1f0457ab14d40 --- /dev/null +++ b/inputs/Question Answering - copa/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Man in a black suit, white shirt and black bow tie playing an instrument with the rest ... +choice1: Somebody has a suit choice2: Nobody has a suit premise: Man in a black suit, white shirt and black bow tie playing an instrument with the rest of his symphony surrounding him. question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_small/Example4.txt b/inputs/Question Answering - copa/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..4362f21b0a9439180d22203b2c5f63e15442ba60 --- /dev/null +++ b/inputs/Question Answering - copa/t5_small/Example4.txt @@ -0,0 +1,2 @@ +At 8:34, the Boston Center controller received a third, transmission from American 11 +choice1: The Boston Center controller got a fourth transmission from American 13 choice2: The Boston Center controller got a third transmission from American 11 premise: At 8:34, the Boston Center controller received a third, transmission from American 11 question: effect \ No newline at end of file diff --git a/inputs/Question Answering - copa/t5_small/Example5.txt b/inputs/Question Answering - copa/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..f8f5d8672e5a9effd04b8aa9f6d187bcab0ab62d --- /dev/null +++ b/inputs/Question Answering - copa/t5_small/Example5.txt @@ -0,0 +1,2 @@ +Cats with long hair shed all over the house so you should not get a long-haired cat +choice1: Long hair cats are bad choice2: Long hair cats are good premise: Cats with long hair shed all over the house so you should not get a long-haired cat question: effect \ No newline at end of file diff --git a/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example1.txt b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..b4667a12c35ca2195bead4b3a256eee323610cb1 --- /dev/null +++ b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example1.txt @@ -0,0 +1,2 @@ +Who is Clark Kent? +Who is Clark Kent? \ No newline at end of file diff --git a/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example2.txt b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..582559703ea66eb7e33c311d08aec9feb22e6fb7 --- /dev/null +++ b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example2.txt @@ -0,0 +1,2 @@ +who is the most famous singer? +who is the most famous singer? \ No newline at end of file diff --git a/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example3.txt b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..c119be42b95b327a09c6535bd45a7e71076e8cac --- /dev/null +++ b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example3.txt @@ -0,0 +1,2 @@ +when do we have winters? +when do we have winters? \ No newline at end of file diff --git a/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example4.txt b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..656b1e524a627ce78d880c68ee58a5b53658627e --- /dev/null +++ b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example4.txt @@ -0,0 +1,2 @@ +In which city is Eiffel Tower located? +In which city is Eiffel Tower located? \ No newline at end of file diff --git a/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example5.txt b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..944355a83e8e1c5a87a3c6731e8c4e4a7d3bd925 --- /dev/null +++ b/inputs/Question Answering - qa/google_t5_small_ssm_nq/Example5.txt @@ -0,0 +1,2 @@ +Who is the founder of Microsoft? +Who is the founder of Microsoft? \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_base/Example1.txt b/inputs/Question Answering - squad/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..b2bb7b38afdd98d146e00ca17a57866740837aba --- /dev/null +++ b/inputs/Question Answering - squad/t5_base/Example1.txt @@ -0,0 +1,2 @@ +What does increased oxygen concentrations in the patient’s lungs displace? +What does increased oxygen concentrations in the patient’s lungs displace? context: Hyperbaric (high-pressure) medicine uses special oxygen chambers to increase the partial pressure of O 2 around the patient and, when needed, the medical staff. Carbon monoxide poisoning, gas gangrene, and decompression sickness (the ’bends’) are sometimes treated using these devices. Increased O 2 concentration in the lungs helps to displace carbon monoxide from the heme group of hemoglobin. Oxygen gas is poisonous to the anaerobic bacteria that cause gas gangrene, so increasing its partial pressure helps kill them. Decompression sickness occurs in divers who decompress too quickly after a dive, resulting in bubbles of inert gas, mostly nitrogen and helium, forming in their blood. Increasing the pressure of O 2 as soon as possible is part of the treatment. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_base/Example2.txt b/inputs/Question Answering - squad/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..2115a36a0e6f29ea2d9ae2b3b84c4e2ff926cbad --- /dev/null +++ b/inputs/Question Answering - squad/t5_base/Example2.txt @@ -0,0 +1,2 @@ +What is the most important thing about being a writer? +What is the most important thing about being a writer? context: If you wish to be a writer, you must learn to develop your own point of view. All good writers make us see things in a different light. You may be writing about the same thing as your classmates, but your presentation must reflect your personality and individuality. There are so many interesting subjects you can write about in different forms but here we will try to attempt writing short stories. There is a good market for the following types: the humorous stories, the adventurous stories, the domestic stories, the mysteries and stories related to animals and strange experiences. Don’t worry if your story turns out to be short – some of the best stories are quite short. Be very careful about’the climax or end of the story. It must be what the reader fears, desires, expects or best of all doesn’t expect. So, get down to it. Think of a plot-make points on how the story will progress and pen it down. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_base/Example3.txt b/inputs/Question Answering - squad/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..03c0f945a3f25e1a79df06ede20fa8eaf962ca1e --- /dev/null +++ b/inputs/Question Answering - squad/t5_base/Example3.txt @@ -0,0 +1,2 @@ +What do most of the people like to read? +What do most of the people like to read? context: If you wish to be a writer, you must learn to develop your own point of view. All good writers make us see things in a different light. You may be writing about the same thing as your classmates, but your presentation must reflect your personality and individuality. There are so many interesting subjects you can write about in different forms but here we will try to attempt writing short stories. There is a good market for the following types: the humorous stories, the adventurous stories, the domestic stories, the mysteries and stories related to animals and strange experiences. Don’t worry if your story turns out to be short – some of the best stories are quite short. Be very careful about’the climax or end of the story. It must be what the reader fears, desires, expects or best of all doesn’t expect. So, get down to it. Think of a plot-make points on how the story will progress and pen it down. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_base/Example4.txt b/inputs/Question Answering - squad/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..b842d538ea2922c90750fe95dc0933c5f753ba14 --- /dev/null +++ b/inputs/Question Answering - squad/t5_base/Example4.txt @@ -0,0 +1,2 @@ +What does a successful writer’s presentation must reflect? +What does a successful writer’s presentation must reflect? context: If you wish to be a writer, you must learn to develop your own point of view. All good writers make us see things in a different light. You may be writing about the same thing as your classmates, but your presentation must reflect your personality and individuality. There are so many interesting subjects you can write about in different forms but here we will try to attempt writing short stories. There is a good market for the following types: the humorous stories, the adventurous stories, the domestic stories, the mysteries and stories related to animals and strange experiences. Don’t worry if your story turns out to be short – some of the best stories are quite short. Be very careful about’the climax or end of the story. It must be what the reader fears, desires, expects or best of all doesn’t expect. So, get down to it. Think of a plot-make points on how the story will progress and pen it down. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_small/Example1.txt b/inputs/Question Answering - squad/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..12e53ae13c959d54cb8d2f5c08d60ae52e9d025c --- /dev/null +++ b/inputs/Question Answering - squad/t5_small/Example1.txt @@ -0,0 +1,2 @@ +What does increased oxygen concentrations in the patient’s lungs displace? ... +What does increased oxygen concentrations in the patient’s lungs displace? context: Hyperbaric (high-pressure) medicine uses special oxygen chambers to increase the partial pressure of O 2 around the patient and, when needed, the medical staff. Carbon monoxide poisoning, gas gangrene, and decompression sickness (the ’bends’) are sometimes treated using these devices. Increased O 2 concentration in the lungs helps to displace carbon monoxide from the heme group of hemoglobin. Oxygen gas is poisonous to the anaerobic bacteria that cause gas gangrene, so increasing its partial pressure helps kill them. Decompression sickness occurs in divers who decompress too quickly after a dive, resulting in bubbles of inert gas, mostly nitrogen and helium, forming in their blood. Increasing the pressure of O 2 as soon as possible is part of the treatment. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_small/Example2.txt b/inputs/Question Answering - squad/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..2115a36a0e6f29ea2d9ae2b3b84c4e2ff926cbad --- /dev/null +++ b/inputs/Question Answering - squad/t5_small/Example2.txt @@ -0,0 +1,2 @@ +What is the most important thing about being a writer? +What is the most important thing about being a writer? context: If you wish to be a writer, you must learn to develop your own point of view. All good writers make us see things in a different light. You may be writing about the same thing as your classmates, but your presentation must reflect your personality and individuality. There are so many interesting subjects you can write about in different forms but here we will try to attempt writing short stories. There is a good market for the following types: the humorous stories, the adventurous stories, the domestic stories, the mysteries and stories related to animals and strange experiences. Don’t worry if your story turns out to be short – some of the best stories are quite short. Be very careful about’the climax or end of the story. It must be what the reader fears, desires, expects or best of all doesn’t expect. So, get down to it. Think of a plot-make points on how the story will progress and pen it down. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_small/Example3.txt b/inputs/Question Answering - squad/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..03c0f945a3f25e1a79df06ede20fa8eaf962ca1e --- /dev/null +++ b/inputs/Question Answering - squad/t5_small/Example3.txt @@ -0,0 +1,2 @@ +What do most of the people like to read? +What do most of the people like to read? context: If you wish to be a writer, you must learn to develop your own point of view. All good writers make us see things in a different light. You may be writing about the same thing as your classmates, but your presentation must reflect your personality and individuality. There are so many interesting subjects you can write about in different forms but here we will try to attempt writing short stories. There is a good market for the following types: the humorous stories, the adventurous stories, the domestic stories, the mysteries and stories related to animals and strange experiences. Don’t worry if your story turns out to be short – some of the best stories are quite short. Be very careful about’the climax or end of the story. It must be what the reader fears, desires, expects or best of all doesn’t expect. So, get down to it. Think of a plot-make points on how the story will progress and pen it down. \ No newline at end of file diff --git a/inputs/Question Answering - squad/t5_small/Example4.txt b/inputs/Question Answering - squad/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..b842d538ea2922c90750fe95dc0933c5f753ba14 --- /dev/null +++ b/inputs/Question Answering - squad/t5_small/Example4.txt @@ -0,0 +1,2 @@ +What does a successful writer’s presentation must reflect? +What does a successful writer’s presentation must reflect? context: If you wish to be a writer, you must learn to develop your own point of view. All good writers make us see things in a different light. You may be writing about the same thing as your classmates, but your presentation must reflect your personality and individuality. There are so many interesting subjects you can write about in different forms but here we will try to attempt writing short stories. There is a good market for the following types: the humorous stories, the adventurous stories, the domestic stories, the mysteries and stories related to animals and strange experiences. Don’t worry if your story turns out to be short – some of the best stories are quite short. Be very careful about’the climax or end of the story. It must be what the reader fears, desires, expects or best of all doesn’t expect. So, get down to it. Think of a plot-make points on how the story will progress and pen it down. \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_base/Example1.txt b/inputs/Sentence Classification - cola/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..eed3ce1da65a066b5fbc2f715d92e1d50494282d --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_base/Example1.txt @@ -0,0 +1,2 @@ +Anna and Mike is going skiing and they is liked is +Anna and Mike is going skiing and they is liked is \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_base/Example2.txt b/inputs/Sentence Classification - cola/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..bd74e6c60af1cc4650e1e85787b6a0afcf40a51e --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Sachin and Virat like to dance +Sachin and Virat like to dance \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_base/Example3.txt b/inputs/Sentence Classification - cola/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b7dcf4ad4f7d012db8a925ff7458a288e6a3eb8c --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_base/Example3.txt @@ -0,0 +1,2 @@ +When the girls on the team to the hotel, they dropped off her luggage +When the girls on the team to the hotel, they dropped off her luggage \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_base/Example4.txt b/inputs/Sentence Classification - cola/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..1da3354cc941c7dd4a44ba351ae48d208f0f6682 --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_base/Example4.txt @@ -0,0 +1,2 @@ +I fed all its fish, then cleaned their tank +I fed all its fish, then cleaned their tank \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_base/Example5.txt b/inputs/Sentence Classification - cola/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..f41f0e4a6a31bba9f35f1c3566e2f6ba686cf64a --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_base/Example5.txt @@ -0,0 +1,2 @@ +A sentence requires at least a subject and a verb, and sometimes an object +A sentence requires at least a subject and a verb, and sometimes an object \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_small/Example1.txt b/inputs/Sentence Classification - cola/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..eed3ce1da65a066b5fbc2f715d92e1d50494282d --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_small/Example1.txt @@ -0,0 +1,2 @@ +Anna and Mike is going skiing and they is liked is +Anna and Mike is going skiing and they is liked is \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_small/Example2.txt b/inputs/Sentence Classification - cola/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..725411c99a1df715efddf8f020bec9065c98c7f8 --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Anna and Mike like to dance +Anna and Mike like to dance \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_small/Example3.txt b/inputs/Sentence Classification - cola/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b7dcf4ad4f7d012db8a925ff7458a288e6a3eb8c --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_small/Example3.txt @@ -0,0 +1,2 @@ +When the girls on the team to the hotel, they dropped off her luggage +When the girls on the team to the hotel, they dropped off her luggage \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_small/Example4.txt b/inputs/Sentence Classification - cola/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..1da3354cc941c7dd4a44ba351ae48d208f0f6682 --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_small/Example4.txt @@ -0,0 +1,2 @@ +I fed all its fish, then cleaned their tank +I fed all its fish, then cleaned their tank \ No newline at end of file diff --git a/inputs/Sentence Classification - cola/t5_small/Example5.txt b/inputs/Sentence Classification - cola/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..f41f0e4a6a31bba9f35f1c3566e2f6ba686cf64a --- /dev/null +++ b/inputs/Sentence Classification - cola/t5_small/Example5.txt @@ -0,0 +1,2 @@ +A sentence requires at least a subject and a verb, and sometimes an object +A sentence requires at least a subject and a verb, and sometimes an object \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_base/Example1.txt b/inputs/Sentiment Analysis - sst2/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..2c90985fb8ac99a726e54298bd7422cac64d15ea --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_base/Example1.txt @@ -0,0 +1,2 @@ +I really hated that movie +I really hated that movie \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_base/Example2.txt b/inputs/Sentiment Analysis - sst2/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..338c1a68852c8a785be9c9d3199b827e506beaaa --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_base/Example2.txt @@ -0,0 +1,2 @@ +it confirms fincher ’s status as a film maker who artfully bends technical know-how to the ... +it confirms fincher ’s status as a film maker who artfully bends technical know-how to the service of psychological insight \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_base/Example3.txt b/inputs/Sentiment Analysis - sst2/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..4a7fff78422a17ac6bc51695409eb42a377be55e --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_base/Example3.txt @@ -0,0 +1,2 @@ +@AmericanAir just landed - 3hours Late Flight - and now we need to wait TWENTY ... +@AmericanAir just landed - 3hours Late Flight - and now we need to wait TWENTY MORE MINUTES for a gate! I have patience but none for incompetence. \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_base/Example4.txt b/inputs/Sentiment Analysis - sst2/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..ba0ee8047316b220188537cfd89008e8195b7a6d --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_base/Example4.txt @@ -0,0 +1,2 @@ +High quality pants. Very comfortable and great for sport activities. Good ... +High quality pants. Very comfortable and great for sport activities. Good price for nice quality! I recommend to all fans of sports \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_base/Example5.txt b/inputs/Sentiment Analysis - sst2/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..910eea4791b18844f15eecc946b990f1a261fee8 --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_base/Example5.txt @@ -0,0 +1,2 @@ +Very frustrated right now. Instagram keeps closing when I log in... +Very frustrated right now. Instagram keeps closing when I log in. Can you help? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_small/Example1.txt b/inputs/Sentiment Analysis - sst2/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..2c90985fb8ac99a726e54298bd7422cac64d15ea --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_small/Example1.txt @@ -0,0 +1,2 @@ +I really hated that movie +I really hated that movie \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_small/Example2.txt b/inputs/Sentiment Analysis - sst2/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..338c1a68852c8a785be9c9d3199b827e506beaaa --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_small/Example2.txt @@ -0,0 +1,2 @@ +it confirms fincher ’s status as a film maker who artfully bends technical know-how to the ... +it confirms fincher ’s status as a film maker who artfully bends technical know-how to the service of psychological insight \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_small/Example3.txt b/inputs/Sentiment Analysis - sst2/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..4a7fff78422a17ac6bc51695409eb42a377be55e --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_small/Example3.txt @@ -0,0 +1,2 @@ +@AmericanAir just landed - 3hours Late Flight - and now we need to wait TWENTY ... +@AmericanAir just landed - 3hours Late Flight - and now we need to wait TWENTY MORE MINUTES for a gate! I have patience but none for incompetence. \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_small/Example4.txt b/inputs/Sentiment Analysis - sst2/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..ba0ee8047316b220188537cfd89008e8195b7a6d --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_small/Example4.txt @@ -0,0 +1,2 @@ +High quality pants. Very comfortable and great for sport activities. Good ... +High quality pants. Very comfortable and great for sport activities. Good price for nice quality! I recommend to all fans of sports \ No newline at end of file diff --git a/inputs/Sentiment Analysis - sst2/t5_small/Example5.txt b/inputs/Sentiment Analysis - sst2/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..910eea4791b18844f15eecc946b990f1a261fee8 --- /dev/null +++ b/inputs/Sentiment Analysis - sst2/t5_small/Example5.txt @@ -0,0 +1,2 @@ +Very frustrated right now. Instagram keeps closing when I log in... +Very frustrated right now. Instagram keeps closing when I log in. Can you help? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_base/Example1.txt b/inputs/Sentiment Analysis - stsb/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..dab410b80b58e9db6755bed3b78fd51d0630492d --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_base/Example1.txt @@ -0,0 +1,2 @@ +sentence1: What attributes would have made you highly desirable in ancient Rome? +sentence1: What attributes would have made you highly desirable in ancient Rome? sentence2: How I GET OPPERTINUTY TO JOIN IT COMPANY AS A FRESHER? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_base/Example2.txt b/inputs/Sentiment Analysis - stsb/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..5bbf7442ed05a5644a075243bca5886ec09e4756 --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_base/Example2.txt @@ -0,0 +1,2 @@ +sentence1: What was it like in Ancient rome? +sentence1: What was it like in Ancient rome? sentence2: What was Ancient rome like? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_base/Example3.txt b/inputs/Sentiment Analysis - stsb/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..4686507e5dff1727d1dc3369aace2dc53788ecb0 --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_base/Example3.txt @@ -0,0 +1,2 @@ +sentence1: How can I install Windows software or games? +sentence1: How can I install Windows software or games? sentence2: I cannot install Windows. How to install it? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_base/Example4.txt b/inputs/Sentiment Analysis - stsb/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..bd6257d54a6b6266f5e8553f06bb1170c190a81a --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_base/Example4.txt @@ -0,0 +1,2 @@ +sentence1: Could you live without the internet? +sentence1: Could you live without the internet? sentence2: Internet is not available for a few days. Could you manage without it? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_base/Example5.txt b/inputs/Sentiment Analysis - stsb/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..971ebab0edaa8bfe23916214aff2a450fd5a251c --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_base/Example5.txt @@ -0,0 +1,2 @@ +sentence1: What is the best thing that happened to you during the past week? +sentence1: What is the best thing that happened to you during the past week? sentence2: What is the best thing that happened to you during the past year? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_small/Example1.txt b/inputs/Sentiment Analysis - stsb/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..dab410b80b58e9db6755bed3b78fd51d0630492d --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_small/Example1.txt @@ -0,0 +1,2 @@ +sentence1: What attributes would have made you highly desirable in ancient Rome? +sentence1: What attributes would have made you highly desirable in ancient Rome? sentence2: How I GET OPPERTINUTY TO JOIN IT COMPANY AS A FRESHER? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_small/Example2.txt b/inputs/Sentiment Analysis - stsb/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..5bbf7442ed05a5644a075243bca5886ec09e4756 --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_small/Example2.txt @@ -0,0 +1,2 @@ +sentence1: What was it like in Ancient rome? +sentence1: What was it like in Ancient rome? sentence2: What was Ancient rome like? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_small/Example3.txt b/inputs/Sentiment Analysis - stsb/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..4686507e5dff1727d1dc3369aace2dc53788ecb0 --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_small/Example3.txt @@ -0,0 +1,2 @@ +sentence1: How can I install Windows software or games? +sentence1: How can I install Windows software or games? sentence2: I cannot install Windows. How to install it? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_small/Example4.txt b/inputs/Sentiment Analysis - stsb/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..bd6257d54a6b6266f5e8553f06bb1170c190a81a --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_small/Example4.txt @@ -0,0 +1,2 @@ +sentence1: Could you live without the internet? +sentence1: Could you live without the internet? sentence2: Internet is not available for a few days. Could you manage without it? \ No newline at end of file diff --git a/inputs/Sentiment Analysis - stsb/t5_small/Example5.txt b/inputs/Sentiment Analysis - stsb/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..971ebab0edaa8bfe23916214aff2a450fd5a251c --- /dev/null +++ b/inputs/Sentiment Analysis - stsb/t5_small/Example5.txt @@ -0,0 +1,2 @@ +sentence1: What is the best thing that happened to you during the past week? +sentence1: What is the best thing that happened to you during the past week? sentence2: What is the best thing that happened to you during the past year? \ No newline at end of file diff --git a/inputs/Text - summarization/t5_base/Example1.txt b/inputs/Text - summarization/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..f248b3dfca8ef999c075030640f917e4a528c1ac --- /dev/null +++ b/inputs/Text - summarization/t5_base/Example1.txt @@ -0,0 +1,2 @@ +Natural language processing (NLP) is a key component in many data science systems that must understand or reason about a text. Common use cases... +Natural language processing (NLP) is a key component in many data science systems that must understand or reason about a text. Common use cases include question answering, paraphrasing or summarizing, sentiment analysis, natural language BI, language modelling, and disambiguation. Nevertheless, NLP is always just a part of a bigger data processing pipeline and due to the nontrivial steps involved in this process, there is a growing need for all-in-one solution to ease the burden of text preprocessing at large scale and connecting the dots between various steps of solving a data science problem with NLP. A good NLP library should be able to correctly transform the free text into structured features and let the users train their own NLP models that are easily fed into the downstream machine learning (ML) or deep learning (DL) pipelines with no hassle \ No newline at end of file diff --git a/inputs/Text - summarization/t5_base/Example2.txt b/inputs/Text - summarization/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..c0cb1fd1d130b8e52d40e1d0cf20dc687f5a5c26 --- /dev/null +++ b/inputs/Text - summarization/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Spark NLP’s annotators utilize rule-based algorithms, machine learning and deep learning models which are implemented using TensorFlow... +Spark NLP’s annotators utilize rule-based algorithms, machine learning and deep learning models which are implemented using TensorFlow that has been heavily optimized for accuracy, speed, scalability, and memory utilization. This setup has been tightly integrated with Apache Spark to let the driver node run the entire training using all the available cores on the driver node. There is a CuDAversion of each TensorFlow component to enable training models on GPU when available. The Spark NLP is written in Scala and provides open-source API’s inPython, Java, Scala, and R - so that users do not need to be aware of the under lying implementation details (TensorFlow, Spark, etc.) in order to use it. Since it has an active release cycle (released 26 new versions in 2019 and another 26 in 2020),the latest trends and research in NLP field are embraced and implemented rapidly in a way that could scale well in a cluster setting to allow common NLP pipelines run orders of magnitude faster than what the inherent design limitations of legacy libraries allowed. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_base/Example3.txt b/inputs/Text - summarization/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..ea1a6422797c1daae24de6fd00a5e24d81e54ba7 --- /dev/null +++ b/inputs/Text - summarization/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Spark NLP library has two versions: Open source and enterprise. Open source version has all the features and components that could be expected... +Spark NLP library has two versions: Open source and enterprise. Open source version has all the features and components that could be expected from any NLP library, using the latest DL frameworks and research trends. Enterprise library is licensed (free for academic purposes) and designed towards solving real world problems in healthcare domain and extends the open source version. The licensed version has the following modules to help researchers and data practitioners in various means: Named entity recognition (NER), assertion status (negativity scope)detection, relation extraction, entity resolution (SNOMED, RxNorm, ICD10 etc.),clinical spell checking, contextual parser, text2SQL, de-identification and obfuscation. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_base/Example4.txt b/inputs/Text - summarization/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..50942302f99930e28e65227b48b7dbac7e4135e5 --- /dev/null +++ b/inputs/Text - summarization/t5_base/Example4.txt @@ -0,0 +1,2 @@ +John Snow (15 March 1813 – 16 June 1858) was an English physician and a leader in the development of anaesthesia and medical hygiene... +John Snow (15 March 1813 – 16 June 1858) was an English physician and a leader in the development of anaesthesia and medical hygiene. He is considered one of the founders of modern epidemiology, in part because of his work in tracing the source of a cholera outbreak in Soho, London, in 1854, which he curtailed by removing the handle of a water pump. Snow's findings inspired the adoption of anaesthesia as well as fundamental changes in the water and waste systems of London, which led to similar changes in other cities, and a significant improvement in general public health around the world. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_base/Example5.txt b/inputs/Text - summarization/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..aa25dec39bfcb0a2111c305b9368dacd98c1b80b --- /dev/null +++ b/inputs/Text - summarization/t5_base/Example5.txt @@ -0,0 +1,2 @@ +As the creator of Spark NLP, John Snow Labs company has been supporting the researchers around the globe by distributing them a free license... +As the creator of Spark NLP, John Snow Labs company has been supporting the researchers around the globe by distributing them a free license to use all the licensed modules both in research projects and graduate level courses at universities,providing hands-on supports when needed, organizing workshops and summits to gather distinguished speakers and running projects with the R&D teams of the top pharmacy companies to help them unlock the potential of unstructured text data buried in their ecosystem. Spark NLP already powers leading healthcare and pharmaceutical companies including Kaiser Permanente, McKesson, Merck, and Roche. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_small/Example1.txt b/inputs/Text - summarization/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..f248b3dfca8ef999c075030640f917e4a528c1ac --- /dev/null +++ b/inputs/Text - summarization/t5_small/Example1.txt @@ -0,0 +1,2 @@ +Natural language processing (NLP) is a key component in many data science systems that must understand or reason about a text. Common use cases... +Natural language processing (NLP) is a key component in many data science systems that must understand or reason about a text. Common use cases include question answering, paraphrasing or summarizing, sentiment analysis, natural language BI, language modelling, and disambiguation. Nevertheless, NLP is always just a part of a bigger data processing pipeline and due to the nontrivial steps involved in this process, there is a growing need for all-in-one solution to ease the burden of text preprocessing at large scale and connecting the dots between various steps of solving a data science problem with NLP. A good NLP library should be able to correctly transform the free text into structured features and let the users train their own NLP models that are easily fed into the downstream machine learning (ML) or deep learning (DL) pipelines with no hassle \ No newline at end of file diff --git a/inputs/Text - summarization/t5_small/Example2.txt b/inputs/Text - summarization/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..c0cb1fd1d130b8e52d40e1d0cf20dc687f5a5c26 --- /dev/null +++ b/inputs/Text - summarization/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Spark NLP’s annotators utilize rule-based algorithms, machine learning and deep learning models which are implemented using TensorFlow... +Spark NLP’s annotators utilize rule-based algorithms, machine learning and deep learning models which are implemented using TensorFlow that has been heavily optimized for accuracy, speed, scalability, and memory utilization. This setup has been tightly integrated with Apache Spark to let the driver node run the entire training using all the available cores on the driver node. There is a CuDAversion of each TensorFlow component to enable training models on GPU when available. The Spark NLP is written in Scala and provides open-source API’s inPython, Java, Scala, and R - so that users do not need to be aware of the under lying implementation details (TensorFlow, Spark, etc.) in order to use it. Since it has an active release cycle (released 26 new versions in 2019 and another 26 in 2020),the latest trends and research in NLP field are embraced and implemented rapidly in a way that could scale well in a cluster setting to allow common NLP pipelines run orders of magnitude faster than what the inherent design limitations of legacy libraries allowed. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_small/Example3.txt b/inputs/Text - summarization/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..ea1a6422797c1daae24de6fd00a5e24d81e54ba7 --- /dev/null +++ b/inputs/Text - summarization/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Spark NLP library has two versions: Open source and enterprise. Open source version has all the features and components that could be expected... +Spark NLP library has two versions: Open source and enterprise. Open source version has all the features and components that could be expected from any NLP library, using the latest DL frameworks and research trends. Enterprise library is licensed (free for academic purposes) and designed towards solving real world problems in healthcare domain and extends the open source version. The licensed version has the following modules to help researchers and data practitioners in various means: Named entity recognition (NER), assertion status (negativity scope)detection, relation extraction, entity resolution (SNOMED, RxNorm, ICD10 etc.),clinical spell checking, contextual parser, text2SQL, de-identification and obfuscation. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_small/Example4.txt b/inputs/Text - summarization/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..50942302f99930e28e65227b48b7dbac7e4135e5 --- /dev/null +++ b/inputs/Text - summarization/t5_small/Example4.txt @@ -0,0 +1,2 @@ +John Snow (15 March 1813 – 16 June 1858) was an English physician and a leader in the development of anaesthesia and medical hygiene... +John Snow (15 March 1813 – 16 June 1858) was an English physician and a leader in the development of anaesthesia and medical hygiene. He is considered one of the founders of modern epidemiology, in part because of his work in tracing the source of a cholera outbreak in Soho, London, in 1854, which he curtailed by removing the handle of a water pump. Snow's findings inspired the adoption of anaesthesia as well as fundamental changes in the water and waste systems of London, which led to similar changes in other cities, and a significant improvement in general public health around the world. \ No newline at end of file diff --git a/inputs/Text - summarization/t5_small/Example5.txt b/inputs/Text - summarization/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..aa25dec39bfcb0a2111c305b9368dacd98c1b80b --- /dev/null +++ b/inputs/Text - summarization/t5_small/Example5.txt @@ -0,0 +1,2 @@ +As the creator of Spark NLP, John Snow Labs company has been supporting the researchers around the globe by distributing them a free license... +As the creator of Spark NLP, John Snow Labs company has been supporting the researchers around the globe by distributing them a free license to use all the licensed modules both in research projects and graduate level courses at universities,providing hands-on supports when needed, organizing workshops and summits to gather distinguished speakers and running projects with the R&D teams of the top pharmacy companies to help them unlock the potential of unstructured text data buried in their ecosystem. Spark NLP already powers leading healthcare and pharmaceutical companies including Kaiser Permanente, McKesson, Merck, and Roche. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_base/Example1.txt b/inputs/Translation - wmt1/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..e16979180d6fa1988e9534cde490b31cc485bfab --- /dev/null +++ b/inputs/Translation - wmt1/t5_base/Example1.txt @@ -0,0 +1,2 @@ +I like sausage and Tea for breakfast with potatoes. +I like sausage and Tea for breakfast with potatoes. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_base/Example2.txt b/inputs/Translation - wmt1/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..19735278785f5dfac06f7fd1ac1ba0ad9c654d2d --- /dev/null +++ b/inputs/Translation - wmt1/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Other than being the king of the north, John Snow is a an english physician and a leader in the d... +Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1834. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_base/Example3.txt b/inputs/Translation - wmt1/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b67103fb0d6a3a69a6700bc5e3a9503a49fc0c6a --- /dev/null +++ b/inputs/Translation - wmt1/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-... +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_base/Example4.txt b/inputs/Translation - wmt1/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..87071834803730909d39d84ffe74a32f9a45bb40 --- /dev/null +++ b/inputs/Translation - wmt1/t5_base/Example4.txt @@ -0,0 +1,2 @@ +William Henry Gates III (born October 28, 1955) is an American business magnate, software develop... +William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_base/Example5.txt b/inputs/Translation - wmt1/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..3de182835fcad5ccf8481fbf059dd6a42ae9193a --- /dev/null +++ b/inputs/Translation - wmt1/t5_base/Example5.txt @@ -0,0 +1,2 @@ +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_small/Example1.txt b/inputs/Translation - wmt1/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..e16979180d6fa1988e9534cde490b31cc485bfab --- /dev/null +++ b/inputs/Translation - wmt1/t5_small/Example1.txt @@ -0,0 +1,2 @@ +I like sausage and Tea for breakfast with potatoes. +I like sausage and Tea for breakfast with potatoes. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_small/Example2.txt b/inputs/Translation - wmt1/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..19735278785f5dfac06f7fd1ac1ba0ad9c654d2d --- /dev/null +++ b/inputs/Translation - wmt1/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Other than being the king of the north, John Snow is a an english physician and a leader in the d... +Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1834. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_small/Example3.txt b/inputs/Translation - wmt1/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b67103fb0d6a3a69a6700bc5e3a9503a49fc0c6a --- /dev/null +++ b/inputs/Translation - wmt1/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-... +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_small/Example4.txt b/inputs/Translation - wmt1/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..87071834803730909d39d84ffe74a32f9a45bb40 --- /dev/null +++ b/inputs/Translation - wmt1/t5_small/Example4.txt @@ -0,0 +1,2 @@ +William Henry Gates III (born October 28, 1955) is an American business magnate, software develop... +William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s. \ No newline at end of file diff --git a/inputs/Translation - wmt1/t5_small/Example5.txt b/inputs/Translation - wmt1/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..3de182835fcad5ccf8481fbf059dd6a42ae9193a --- /dev/null +++ b/inputs/Translation - wmt1/t5_small/Example5.txt @@ -0,0 +1,2 @@ +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_base/Example1.txt b/inputs/Translation - wmt2/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..e16979180d6fa1988e9534cde490b31cc485bfab --- /dev/null +++ b/inputs/Translation - wmt2/t5_base/Example1.txt @@ -0,0 +1,2 @@ +I like sausage and Tea for breakfast with potatoes. +I like sausage and Tea for breakfast with potatoes. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_base/Example2.txt b/inputs/Translation - wmt2/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..19735278785f5dfac06f7fd1ac1ba0ad9c654d2d --- /dev/null +++ b/inputs/Translation - wmt2/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Other than being the king of the north, John Snow is a an english physician and a leader in the d... +Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1834. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_base/Example3.txt b/inputs/Translation - wmt2/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b67103fb0d6a3a69a6700bc5e3a9503a49fc0c6a --- /dev/null +++ b/inputs/Translation - wmt2/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-... +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_base/Example4.txt b/inputs/Translation - wmt2/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..87071834803730909d39d84ffe74a32f9a45bb40 --- /dev/null +++ b/inputs/Translation - wmt2/t5_base/Example4.txt @@ -0,0 +1,2 @@ +William Henry Gates III (born October 28, 1955) is an American business magnate, software develop... +William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_base/Example5.txt b/inputs/Translation - wmt2/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..3de182835fcad5ccf8481fbf059dd6a42ae9193a --- /dev/null +++ b/inputs/Translation - wmt2/t5_base/Example5.txt @@ -0,0 +1,2 @@ +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_small/Example1.txt b/inputs/Translation - wmt2/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..e16979180d6fa1988e9534cde490b31cc485bfab --- /dev/null +++ b/inputs/Translation - wmt2/t5_small/Example1.txt @@ -0,0 +1,2 @@ +I like sausage and Tea for breakfast with potatoes. +I like sausage and Tea for breakfast with potatoes. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_small/Example2.txt b/inputs/Translation - wmt2/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..19735278785f5dfac06f7fd1ac1ba0ad9c654d2d --- /dev/null +++ b/inputs/Translation - wmt2/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Other than being the king of the north, John Snow is a an english physician and a leader in the d... +Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1834. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_small/Example3.txt b/inputs/Translation - wmt2/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b67103fb0d6a3a69a6700bc5e3a9503a49fc0c6a --- /dev/null +++ b/inputs/Translation - wmt2/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-... +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_small/Example4.txt b/inputs/Translation - wmt2/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..87071834803730909d39d84ffe74a32f9a45bb40 --- /dev/null +++ b/inputs/Translation - wmt2/t5_small/Example4.txt @@ -0,0 +1,2 @@ +William Henry Gates III (born October 28, 1955) is an American business magnate, software develop... +William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s. \ No newline at end of file diff --git a/inputs/Translation - wmt2/t5_small/Example5.txt b/inputs/Translation - wmt2/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..3de182835fcad5ccf8481fbf059dd6a42ae9193a --- /dev/null +++ b/inputs/Translation - wmt2/t5_small/Example5.txt @@ -0,0 +1,2 @@ +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_base/Example1.txt b/inputs/Translation - wmt3/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..e16979180d6fa1988e9534cde490b31cc485bfab --- /dev/null +++ b/inputs/Translation - wmt3/t5_base/Example1.txt @@ -0,0 +1,2 @@ +I like sausage and Tea for breakfast with potatoes. +I like sausage and Tea for breakfast with potatoes. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_base/Example2.txt b/inputs/Translation - wmt3/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..19735278785f5dfac06f7fd1ac1ba0ad9c654d2d --- /dev/null +++ b/inputs/Translation - wmt3/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Other than being the king of the north, John Snow is a an english physician and a leader in the d... +Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1834. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_base/Example3.txt b/inputs/Translation - wmt3/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b67103fb0d6a3a69a6700bc5e3a9503a49fc0c6a --- /dev/null +++ b/inputs/Translation - wmt3/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-... +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_base/Example4.txt b/inputs/Translation - wmt3/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..87071834803730909d39d84ffe74a32f9a45bb40 --- /dev/null +++ b/inputs/Translation - wmt3/t5_base/Example4.txt @@ -0,0 +1,2 @@ +William Henry Gates III (born October 28, 1955) is an American business magnate, software develop... +William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_base/Example5.txt b/inputs/Translation - wmt3/t5_base/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..3de182835fcad5ccf8481fbf059dd6a42ae9193a --- /dev/null +++ b/inputs/Translation - wmt3/t5_base/Example5.txt @@ -0,0 +1,2 @@ +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_small/Example1.txt b/inputs/Translation - wmt3/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..e16979180d6fa1988e9534cde490b31cc485bfab --- /dev/null +++ b/inputs/Translation - wmt3/t5_small/Example1.txt @@ -0,0 +1,2 @@ +I like sausage and Tea for breakfast with potatoes. +I like sausage and Tea for breakfast with potatoes. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_small/Example2.txt b/inputs/Translation - wmt3/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..19735278785f5dfac06f7fd1ac1ba0ad9c654d2d --- /dev/null +++ b/inputs/Translation - wmt3/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Other than being the king of the north, John Snow is a an english physician and a leader in the d... +Other than being the king of the north, John Snow is a an english physician and a leader in the development of anaesthesia and medical hygiene. He is considered for being the first one using data to cure cholera outbreak in 1834. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_small/Example3.txt b/inputs/Translation - wmt3/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..b67103fb0d6a3a69a6700bc5e3a9503a49fc0c6a --- /dev/null +++ b/inputs/Translation - wmt3/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-... +Titanic is a 1997 American epic romance and disaster film directed, written, co-produced, and co-edited by James Cameron. Incorporating both historical and fictionalized aspects, it is based on accounts of the sinking of the RMS Titanic. It stars Leonardo DiCaprio and Kate Winslet as members of different social classes who fall in love aboard the ship during its ill-fated maiden voyage. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_small/Example4.txt b/inputs/Translation - wmt3/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..87071834803730909d39d84ffe74a32f9a45bb40 --- /dev/null +++ b/inputs/Translation - wmt3/t5_small/Example4.txt @@ -0,0 +1,2 @@ +William Henry Gates III (born October 28, 1955) is an American business magnate, software develop... +William Henry Gates III (born October 28, 1955) is an American business magnate, software developer, investor, and philanthropist. He is best known as the co-founder of Microsoft Corporation. During his career at Microsoft, Gates held the positions of chairman, chief executive officer (CEO), president and chief software architect. He was also being the largest individual shareholder until May 2014. He is one of the best-known entrepreneurs and pioneers of the microcomputer revolution of the 1970s and 1980s. \ No newline at end of file diff --git a/inputs/Translation - wmt3/t5_small/Example5.txt b/inputs/Translation - wmt3/t5_small/Example5.txt new file mode 100644 index 0000000000000000000000000000000000000000..3de182835fcad5ccf8481fbf059dd6a42ae9193a --- /dev/null +++ b/inputs/Translation - wmt3/t5_small/Example5.txt @@ -0,0 +1,2 @@ +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. +The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris. \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_base/Example1.txt b/inputs/Word Sense Disambiguation - wic/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..918da9f21234f6f592341ac6eef8dcd679834b80 --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_base/Example1.txt @@ -0,0 +1,2 @@ +Window +pos: sentence1: The expanded window will give us time to catch the thieves. sentence2: You have a two-hour window of turning in your homework. word: Window \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_base/Example2.txt b/inputs/Word Sense Disambiguation - wic/t5_base/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..fc48607aecfe2ed6f5ff95514de58b7acb1255c6 --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_base/Example2.txt @@ -0,0 +1,2 @@ +Kill +pos: sentence1: He totally killed that rock show! sentence2: The lion killed the dear word: Kill \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_base/Example3.txt b/inputs/Word Sense Disambiguation - wic/t5_base/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..1f091723b07b004017851aa4c340b2a04138a78a --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_base/Example3.txt @@ -0,0 +1,2 @@ +Rich +pos: sentence1: This Milkshake is rich in calcium and other nutrients sentence2: Elon Musk is the richest person word: Rich \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_base/Example4.txt b/inputs/Word Sense Disambiguation - wic/t5_base/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..e4830fd68b5fdf0a115dc291fc842adbe4e9752a --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_base/Example4.txt @@ -0,0 +1,2 @@ +Elephant +pos: sentence1: An elephant in the room is basically a problem or difficult issue that is very obvious, but is ignored for the convenience or comfort of those involved. sentence2: Elephant is a very large animal word: Elephant \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_small/Example1.txt b/inputs/Word Sense Disambiguation - wic/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..918da9f21234f6f592341ac6eef8dcd679834b80 --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_small/Example1.txt @@ -0,0 +1,2 @@ +Window +pos: sentence1: The expanded window will give us time to catch the thieves. sentence2: You have a two-hour window of turning in your homework. word: Window \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_small/Example2.txt b/inputs/Word Sense Disambiguation - wic/t5_small/Example2.txt new file mode 100644 index 0000000000000000000000000000000000000000..fc48607aecfe2ed6f5ff95514de58b7acb1255c6 --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_small/Example2.txt @@ -0,0 +1,2 @@ +Kill +pos: sentence1: He totally killed that rock show! sentence2: The lion killed the dear word: Kill \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_small/Example3.txt b/inputs/Word Sense Disambiguation - wic/t5_small/Example3.txt new file mode 100644 index 0000000000000000000000000000000000000000..1f091723b07b004017851aa4c340b2a04138a78a --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_small/Example3.txt @@ -0,0 +1,2 @@ +Rich +pos: sentence1: This Milkshake is rich in calcium and other nutrients sentence2: Elon Musk is the richest person word: Rich \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wic/t5_small/Example4.txt b/inputs/Word Sense Disambiguation - wic/t5_small/Example4.txt new file mode 100644 index 0000000000000000000000000000000000000000..e4830fd68b5fdf0a115dc291fc842adbe4e9752a --- /dev/null +++ b/inputs/Word Sense Disambiguation - wic/t5_small/Example4.txt @@ -0,0 +1,2 @@ +Elephant +pos: sentence1: An elephant in the room is basically a problem or difficult issue that is very obvious, but is ignored for the convenience or comfort of those involved. sentence2: Elephant is a very large animal word: Elephant \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wsc/t5_base/Example1.txt b/inputs/Word Sense Disambiguation - wsc/t5_base/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..fe1c51b8389dd00d1a4293620edde8dd0e7dbec4 --- /dev/null +++ b/inputs/Word Sense Disambiguation - wsc/t5_base/Example1.txt @@ -0,0 +1,2 @@ +The stable was very roomy, with four good stalls; a large swinging window opened into the yard , ... +The stable was very roomy, with four good stalls; a large swinging window opened into the yard , which made *it* pleasant and airy. \ No newline at end of file diff --git a/inputs/Word Sense Disambiguation - wsc/t5_small/Example1.txt b/inputs/Word Sense Disambiguation - wsc/t5_small/Example1.txt new file mode 100644 index 0000000000000000000000000000000000000000..fe1c51b8389dd00d1a4293620edde8dd0e7dbec4 --- /dev/null +++ b/inputs/Word Sense Disambiguation - wsc/t5_small/Example1.txt @@ -0,0 +1,2 @@ +The stable was very roomy, with four good stalls; a large swinging window opened into the yard , ... +The stable was very roomy, with four good stalls; a large swinging window opened into the yard , which made *it* pleasant and airy. \ No newline at end of file diff --git a/pages/Workflow & Model Overview.py b/pages/Workflow & Model Overview.py new file mode 100644 index 0000000000000000000000000000000000000000..2fdfbdb3d1912f20008f41be680d1e5d76bcaea6 --- /dev/null +++ b/pages/Workflow & Model Overview.py @@ -0,0 +1,218 @@ +import streamlit as st + +# Custom CSS for better styling +st.markdown(""" + +""", unsafe_allow_html=True) + +# Introduction +st.markdown('
State-of-the-Art Text Summarization with Spark NLP
', unsafe_allow_html=True) + +st.markdown(""" +
+

Welcome to the Spark NLP Demos App! In the rapidly evolving field of Natural Language Processing (NLP), the combination of powerful models and scalable frameworks is crucial. One such resource-intensive task is Text Summarization, which benefits immensely from the efficient implementation of machine learning models on distributed systems like Apache Spark.

+

Spark NLP stands out as the leading choice for enterprises building NLP solutions. This open-source library, built in Scala with a Python wrapper, offers state-of-the-art machine learning models within an easy-to-use pipeline design compatible with Spark ML.

+
+""", unsafe_allow_html=True) + +# About the T5 Model +st.markdown('
About the T5 Model
', unsafe_allow_html=True) +st.markdown(""" +
+

A standout model for text summarization is the Text-to-Text Transformer (T5), introduced by Google researchers in 2019. T5 achieves remarkable results by utilizing a unique design that allows it to perform multiple NLP tasks with simple prefixes. For text summarization, the input text is prefixed with "summarize:".

+

In Spark NLP, the T5 model is available through the T5Transformer annotator. We'll show you how to use Spark NLP in Python to perform text summarization using the T5 model.

+
+""", unsafe_allow_html=True) + +st.image('images/T5_model_diagram.jpg', caption='Diagram of the T5 model, from the original paper', use_column_width='auto') + +# Detailed Tasks with T5 Model +st.markdown(""" +
+

The T5 model can handle a wide range of NLP tasks by setting specific task prefixes. Here’s how you can use it for various tasks:

+
+

Sentence Classification - cola

+

Classify if a sentence is grammatically correct. Use the task prefix "cola:".

+

Natural Language Inference (NLI)

+ +

Coreference Resolution

+ +

Sentiment Analysis

+ +

Question Answering

+ +

Word Sense Disambiguation

+

Classify if a word has the same meaning in two sentences. Use "wic:".

+

Text Summarization

+

Summarize text into a shorter representation. Use "summarize:".

+

Translation

+ +

For more details about each task, refer to the T5 paper.

+""", unsafe_allow_html=True) + +# How to Use the Model +st.markdown('
How to Use the T5 Model with Spark NLP
', unsafe_allow_html=True) +st.markdown(""" +
+

To use the T5Transformer annotator in Spark NLP to perform text summarization, we need to create a pipeline with two stages: the first transforms the input text into an annotation object, and the second stage contains the T5 model.

+
+""", unsafe_allow_html=True) + +st.markdown('
Installation
', unsafe_allow_html=True) +st.code('!pip install spark-nlp', language='python') + +st.markdown('
Import Libraries and Start Spark Session
', unsafe_allow_html=True) +st.code(""" +import sparknlp +from sparknlp.base import DocumentAssembler, PipelineModel +from sparknlp.annotator import T5Transformer + +# Start the Spark Session +spark = sparknlp.start() +""", language='python') + +st.markdown(""" +
+

Now we can define the pipeline to use the T5 model. We'll use the PipelineModel object since we are using the pretrained model and don’t need to train any stage of the pipeline.

+
+""", unsafe_allow_html=True) + +st.markdown('
Define the Pipeline
', unsafe_allow_html=True) +st.code(""" +# Transforms raw texts into `document` annotation +document_assembler = ( + DocumentAssembler().setInputCol("text").setOutputCol("documents") +) +# The T5 model +t5 = ( + T5Transformer.pretrained("t5_small") + .setTask("summarize:") + .setInputCols(["documents"]) + .setMaxOutputLength(200) + .setOutputCol("t5") +) +# Define the Spark pipeline +pipeline = PipelineModel(stages = [document_assembler, t5]) +""", language='python') + +st.markdown(""" +
+

To use the model, create a Spark DataFrame containing the input data. In this example, we'll work with a single sentence, but the framework can handle multiple texts for simultaneous processing. The input column from the DocumentAssembler annotator requires a column named “text.”

+
+""", unsafe_allow_html=True) + +st.markdown('
Create Example DataFrame', unsafe_allow_html=True) +st.code(""" +example = \""" +Transfer learning, where a model is first pre-trained on a data-rich task +before being fine-tuned on a downstream task, has emerged as a powerful +technique in natural language processing (NLP). The effectiveness of transfer +learning has given rise to a diversity of approaches, methodology, and +practice. In this paper, we explore the landscape of transfer learning +techniques for NLP by introducing a unified framework that converts all +text-based language problems into a text-to-text format. +Our systematic study compares pre-training objectives, architectures, +unlabeled data sets, transfer approaches, and other factors on dozens of +language understanding tasks. By combining the insights from our exploration +with scale and our new Colossal Clean Crawled Corpus, we achieve +state-of-the-art results on many benchmarks covering summarization, +question answering, text classification, and more. To facilitate future +work on transfer learning for NLP, we release our data set, pre-trained +models, and code. +\""" + +spark_df = spark.createDataFrame([[example]]) +""", language='python') + +st.markdown('
Apply the Pipeline
', unsafe_allow_html=True) +st.code(""" +result = pipeline.transform(spark_df) +result.select("t5.result").show(truncate=False) +""", language='python') + +st.markdown('
Output
', unsafe_allow_html=True) +st.markdown(""" +
+

The summarization output will look something like this:

+ 
transfer learning has emerged as a powerful technique in natural language processing (NLP) the effectiveness of transfer learning has given rise to a diversity of approaches, methodologies, and practice.
+

Note: We defined the maximum output length to 200. Depending on the length of the original text, this parameter should be adapted.

+
+""", unsafe_allow_html=True) + +# Additional Resources and References +st.markdown('
Additional Resources and References
', unsafe_allow_html=True) +st.markdown(""" +
+ +
+""", unsafe_allow_html=True) + +st.markdown('
Community & Support
', unsafe_allow_html=True) +st.markdown(""" +
+ +
+""", unsafe_allow_html=True) + + diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..327c0a2a3aac36b6f2416cf191e5c28edab4a0b4 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,6 @@ +streamlit +st-annotated-text +pandas +numpy +spark-nlp +pyspark \ No newline at end of file