Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| import pandas as pd | |
| import altair as alt | |
| from transformers import pipeline | |
| #!pip install -U sentence-transformers | |
| from sentence_transformers import SentenceTransformer, util | |
| from sentence_transformers import SentenceTransformer | |
| import numpy as np | |
| import sys | |
| import json | |
| #from torch.utils.data import DataLoader | |
| from sentence_transformers import SentenceTransformer, LoggingHandler, util, models, evaluation, losses, InputExample | |
| from torch.utils.data import IterableDataset | |
| import tqdm | |
| #from torch.utils.data import Dataset | |
| import random | |
| from shutil import copyfile | |
| from urllib.error import URLError | |
| ## TEXT ###################################################################################################################### | |
| # Load document embeddings | |
| # set up title and sidebar | |
| st.title (" Nashville Analytics Summit Conference Helper")# (" Your top 3 Important Sessions") | |
| st.markdown("**Problem**🤔: Since its inception in 2013, Nashville Analytics Summit has seen a growth of over 488%. The Summit prides its itself as the fastest growing locally grown tech events in the south region. With an increasing number of participants and dozens of talks covering a myriad of topics, there is a need to tailor participants needs to their interests") | |
| st.markdown("**Solution**💡: Develop an application in which users can input the description of areas of interest and app returns the top three Sessions matching the description requested.") | |
| st.markdown("** Approach**🔑:") | |
| st.markdown("* For the approach, I used a transformer model, multi-qa-MiniLM-L6-cos-v1, that uses sentence similarity to match the description of the event and the input description.") | |
| st.markdown("* The dataset used is Nashville Analytics Summit descriptions of the presentations, which include the Unique ID, Name of presenter, Description of presentation, Activity Code, Start Time, End Time, Location Name") | |
| st.markdown("* Given a {claim, evidence} pair, determine whether the climate claim is supported or refuted (or neither) by the evidence") | |
| st.markdown("---") | |
| st.markdown("## The Details") | |
| # section 1: the context, problem; how to address | |
| st.markdown("### Problem") | |
| st.markdown("With the growth of the Nashville Analytics Summit every year, there have been an increase in the number participants, the number of talks/topics have exponentially increased over time covering a myriad of current issues and developments. This has made it challenging for the participants to easily navigate the event and attend the sessions of interest before reading through the sessions descriptions. Struggling finding the Session that Matches your personal interests? Transformers to the rescue!!!.") | |
| dificult_reading = Image.open('images/dificult_reading.png') | |
| st.image(dificult_reading, caption='Reading sessions descriptions. (1)') | |
| # section 2: how can transformers help? | |
| st.markdown("### How can Transformers Help?💡") | |
| st.markdown("**Sentence Similarity**") | |
| #st.markdown("* FEVER, or Fact Extraction and VERification, was introduced in 2018 as the first dataset containing {fact, evdience, entailment_label} information. They extracted altering sentences from Wikipedia and had annotators report the relationship between the setences: entailment, contradition, not enough information.") | |
| #st.markdown("* Since then, other researchers have expanded on this area in different domains") | |
| #st.markdown("* Here, we use Climate FEVER (3), a similar dataset developed and annotated by ") | |
| #st.markdown("**Fact Verification / Fact-Checking**") | |
| #st.markdown("* This is simply an extenstion of the textual entailment task") | |
| #st.markdown("* Given two sentences, sent1 and sent2, determine the relationship: entail, contradict, neutral") | |
| #st.markdown("* With fact verification, we can think of the sentences as claim and evidence and labels as support, refute, or not enough information to refute or support.") | |
| # section 4: The process | |
| # this is the pipeline in my notes (u are here highlight) | |
| #st.markdown("### The Process 🔑") | |
| #st.markdown("Imagine: A person is curious about whether a claim they heard about climate change is true. How can transformers help validate or refute the claim?") | |
| #st.markdown("1. User inputs a climate claim") | |
| st.markdown("2. Retrieve evidence related to input claim \ | |
| - For each claim, collect N related documents. These documents are selected by finding the N documents with the highest similarity scores to the claim. A current area of research: How do we keep the set of curated documents up-to-date? Validate their contents?") | |
| #st.markdown("3. Send (claim, evidence) pairs to a transformer model. Have the model predict whether each evidence supports, refutes, or is not relevant to the claim. (📍 YOU ARE HERE!)") | |
| #st.markdown("4. Report back to the user: The supporting evidence for the claim (if any), the refuting evidence for the claim (if any). If no relevant evidence is found, report that the claim cannot be supported or refuted by current evidence.") | |
| # section 5: my work | |
| #st.markdown("## Climate Claim Fact-Checking with Transformers") | |
| #st.markdown("My work focuses on step 3 of the process: Training a transformer model to accurately categorize (claim, evidence) as:") | |
| #st.markdown("* evidence *supports* (entails) claim") | |
| #st.markdown("* evidence *refutes* (contradicts) claim") | |
| #st.markdown("* evidence *does not provide enough info to support or refute* (neutral) claim") | |
| #st.markdown("For this project, I fine-tune ClimateBERT (4) on the text entailment task") | |
| ## EXAMPLE ################################################################################################################### | |
| st.markdown("## Try it out!") | |
| st.markdown("This application is a dashboard for displaying your top 3 matching Sessions at the Nashville summit") | |
| doc_emb = np.loadtxt("abstract-embed.txt", dtype=float) | |
| # Load data | |
| df = pd.read_csv("sessions.csv", usecols=['Unique ID', 'Name', 'Description', 'Activity Code', 'Start Time', 'End Time', 'Location Name']) | |
| # front end elements of the web page | |
| html_temp = """ | |
| <div style ="background-color:lightblue;padding:13px"> | |
| <h1 style ="color:white;text-align:center;">Sentence Similarity App for Nashville Analytic Summit 2022</h1> | |
| </div> | |
| """ | |
| def main(): | |
| # display the front end aspect | |
| st.markdown(html_temp, unsafe_allow_html = True) | |
| # Get attributes from dataframe | |
| docs = list(df["Description"]) | |
| titles = list(df["Name"]) | |
| start_times = list(df["Start Time"]) | |
| end_times = list(df["End Time"]) | |
| locations = list(df["Location Name"]) | |
| # Query | |
| # Load the model | |
| model = pipeline('text-classification')#('sentence-transformers/multi-qa-MiniLM-L6-cos-v1') | |
| query = st.text_input("Enter your query: ") | |
| if query: | |
| #st.text_area('Text area') | |
| #age = st.number_input("Age in Years") | |
| #Encode query and documents | |
| query_emb = model(query)#.astype(float) | |
| #Compute dot score between query and all document embeddings | |
| #scores = util.dot_score(query_emb, doc_emb.astype(float))#[0].cpu().tolist() | |
| #cos_scores = util.pytorch_cos_sim(query_emb, doc_emb)[0] | |
| scores = util.pytorch_cos_sim(query_emb, doc_emb)[0] | |
| #Combine docs & scores with other attributes | |
| doc_score_pairs = list(zip(docs, scores, titles, start_times, end_times, locations)) | |
| # top_k results to return | |
| top_k=3 | |
| print(" Your top", top_k, "most similar sessions in the Summit:") | |
| #Sort the results in decreasing order and get the first top_k | |
| doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True) | |
| #Output presentation recommendations | |
| for doc, score, title, start_time, end_time, location in doc_score_pairs[:top_k]: | |
| st.write("Score: %f" %score) | |
| st.write("Title: %s" %title) | |
| st.write("Abstract: %s" %doc) | |
| st.write("Location: %s" %location) | |
| st.write(f"From {start_time} to {end_time}") | |
| st.write('\n') | |
| if __name__ == "__main__": | |
| main() |