Spaces:
Build error
Build error
| import nltk | |
| import streamlit as st | |
| import validators | |
| from transformers import pipeline | |
| from validators import ValidationFailure | |
| from Summarizer import Summarizer | |
| def main() -> None: | |
| nltk.download('punkt') | |
| st.markdown('# Terms & conditions summarization :pencil:') | |
| st.markdown('Do you also take the time out of your day to thoroughly read every word of the Terms & Conditions before signing up for a new app? :thinking_face:<br>' | |
| 'No?<br>' | |
| 'Well have we got a demo for you!', unsafe_allow_html=True) | |
| st.markdown('Just copy-paste the lengthy Terms & Conditions text or provide a URL to the text and let our fancy NLP algorithm do the rest! :brain:<br>' | |
| 'You will see both an extractive summary (the most important sentences will be highlighted) and an abstractive summary (an actual summary)', unsafe_allow_html=True) | |
| st.markdown('Want to find out more?<br>' | |
| 'For details about the extractive part :point_right: https://en.wikipedia.org/wiki/Latent_semantic_analysis<br>' | |
| 'For details about the abstractive part :point_right: https://huggingface.co/ml6team/distilbart-tos-summarizer-tosdr', unsafe_allow_html=True) | |
| def create_pipeline(): | |
| with st.spinner('Please wait for the model to load...'): | |
| terms_and_conditions_pipeline = pipeline( | |
| task='summarization', | |
| model='ml6team/distilbart-tos-summarizer-tosdr', | |
| tokenizer='ml6team/distilbart-tos-summarizer-tosdr' | |
| ) | |
| return terms_and_conditions_pipeline | |
| def display_abstractive_summary(summary) -> None: | |
| st.subheader("Abstractive Summary") | |
| st.markdown('#####') | |
| st.markdown(summary) | |
| def display_extractive_summary(terms_and_conditions_sentences: list, summary_sentences: list) -> None: | |
| st.subheader("Extractive Summary") | |
| st.markdown('#####') | |
| terms_and_conditions = " ".join(sentence for sentence in terms_and_conditions_sentences) | |
| replaced_text = terms_and_conditions | |
| for sentence in summary_sentences: | |
| replaced_text = replaced_text.replace(sentence, | |
| f"<span style='background-color: #FFFF00'>{sentence}</span>") | |
| st.write(replaced_text, unsafe_allow_html=True) | |
| def is_valid_url(url: str) -> bool: | |
| result = validators.url(url) | |
| if isinstance(result, ValidationFailure): | |
| return False | |
| return True | |
| summarizer: Summarizer = Summarizer(create_pipeline()) | |
| if 'tc_text' not in st.session_state: | |
| st.session_state['tc_text'] = '' | |
| if 'sentences_length' not in st.session_state: | |
| st.session_state['sentences_length'] = Summarizer.DEFAULT_EXTRACTED_ARTICLE_SENTENCES_LENGTH | |
| st.write('<style>div.row-widget.stRadio > div{flex-direction:row;}</style>', unsafe_allow_html=True) | |
| st.header("Input") | |
| with st.form(key='terms-and-conditions'): | |
| sentences_length_input = st.number_input( | |
| label='Number of sentences to be extracted:', | |
| min_value=1, | |
| value=st.session_state.sentences_length | |
| ) | |
| tc_text_input = st.text_area( | |
| value=st.session_state.tc_text, | |
| label='Terms & conditions content or specify an URL:', | |
| height=240 | |
| ) | |
| submit_button = st.form_submit_button(label='Summarize') | |
| if submit_button: | |
| if is_valid_url(tc_text_input): | |
| (all_sentences, extract_summary_sentences) = summarizer.extractive_summary_from_url(tc_text_input, | |
| sentences_length_input) | |
| else: | |
| (all_sentences, extract_summary_sentences) = summarizer.extractive_summary_from_text(tc_text_input, | |
| sentences_length_input) | |
| extract_summary = " ".join([sentence for sentence in extract_summary_sentences]) | |
| abstract_summary = summarizer.abstractive_summary(extract_summary) | |
| display_extractive_summary(all_sentences, extract_summary_sentences) | |
| display_abstractive_summary(abstract_summary) | |
| if __name__ == "__main__": | |
| main() | |