Spaces:
Running
Running
File size: 5,530 Bytes
4a26e59 3454d4e 23189bc 3454d4e 4a26e59 23189bc 4a26e59 3454d4e 4a26e59 3454d4e ae23c23 3454d4e 25a1096 ae23c23 3454d4e 25a1096 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 |
import torch
import streamlit as st
from transformers import pipeline, AutoTokenizer, AutoModelForQuestionAnswering
st.set_page_config(page_title="Common NLP Tasks")
st.title("Common NLP Tasks")
st.subheader("Use the menu on the left to select a NLP task to do (click on > if closed).")
expander = st.sidebar.expander('About')
expander.write("This web app allows you to perform common Natural Language Processing tasks, select a task below to get started.")
st.sidebar.header('What will you like to do?')
option = st.sidebar.radio('', ['Extractive question answering', 'Text summarization', 'Text generation', 'Sentiment analysis'])
@st.cache(show_spinner=False, allow_output_mutation=True)
def question_answerer(context, question):
tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2")
model = AutoModelForQuestionAnswering.from_pretrained("deepset/roberta-base-squad2")
inputs = tokenizer(question, context, add_special_tokens=True, return_tensors="pt")
input_ids = inputs["input_ids"].tolist()[0]
outputs = model(**inputs)
answer_start_scores = outputs.start_logits
answer_end_scores = outputs.end_logits
# Get the most likely beginning of answer with the argmax of the score
answer_start = torch.argmax(answer_start_scores)
# Get the most likely end of answer with the argmax of the score
answer_end = torch.argmax(answer_end_scores) + 1
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start:answer_end]))
return answer
@st.cache(show_spinner=False, allow_output_mutation=True)
def summarization_model():
summarizer = pipeline("summarization")
return summarizer
@st.cache(show_spinner=False, allow_output_mutation=True)
def generation_model():
generator = pipeline("text-generation")
return generator
@st.cache(show_spinner=False, allow_output_mutation=True)
def sentiment_model():
sentiment_analysis = pipeline("sentiment-analysis")
return sentiment_analysis
if option == 'Extractive question answering':
st.markdown("<h2 style='text-align: center; color:red;'>Extract answer from text</h2>", unsafe_allow_html=True)
sample_text = "sample text"
source = st.radio("How would you like to start? Choose an option below", ["I want to input some text", "I want to upload a file"])
if source == "I want to input some text":
context = st.text_area('Use the example below or input your own text in English (between 1,000 and 10,000 characters)', value=sample_text, max_chars=10000, height=330)
question = st.text_input(label='Enter your question')
button = st.button('Get answer')
if button:
with st.spinner(text="Getting answer..."):
answer = question_answerer(context, question)
st.write(answer)
elif source == "I want to upload a file":
uploaded_file = st.file_uploader("Choose a .txt file to upload", type=["txt"])
question = st.text_input(label='Enter your question')
button = st.button('Get answer')
if button:
question_answerer = question_model()
with st.spinner(text="Getting answer..."):
answer = question_answerer(context=context, question=question)
st.write(answer["answer"])
elif option == 'Text summarization':
st.markdown("<h2 style='text-align: center; color:red;'>Summarize text</h2>", unsafe_allow_html=True)
sample_text = "sample text"
source = st.radio("How would you like to start? Choose an option below", ["I want to input some text", "I want to upload a file"])
if source == "I want to input some text":
text = st.text_area('Input a text in English (between 1,000 and 10,000 characters)', value=sample_text, max_chars=10000, height=330)
button = st.button('Get summary')
if button:
summarizer = summarization_model()
with st.spinner(text="Summarizing text..."):
summary = summarizer(text, max_length=130, min_length=30)
st.write(summary)
elif source == "I want to upload a file":
uploaded_file = st.file_uploader("Choose a .txt file to upload", type=["txt"])
button = st.button('Get summary')
if button:
summarizer = summarization_model()
with st.spinner(text="Summarizing text..."):
summary = summarizer(text, max_length=130, min_length=30)
st.write(summary)
elif option == 'Text generation':
st.markdown("<h2 style='text-align: center; color:grey;'>Generate text</h2>", unsafe_allow_html=True)
text = st.text_input(label='Enter one line of text and let the NLP model generate the rest for you')
button = st.button('Generate text')
if button:
generator = generation_model()
with st.spinner(text="Generating text..."):
generated_text = generator(text, max_length=50)
st.write(generated_text[0]["generated_text"])
elif option == 'Sentiment analysis':
st.markdown("<h2 style='text-align: center; color:grey;'>Classify review</h2>", unsafe_allow_html=True)
text = st.text_input(label='Enter a sentence to get its sentiment analysis')
button = st.button('Get sentiment analysis')
if button:
sentiment_analysis = sentiment_model()
with st.spinner(text="Getting sentiment analysis..."):
sentiment = sentiment_analysis(text)
st.write(sentiment[0]["label"]) |