# TopicDig

### TopicDig enables on-the-fly news digest creation via named entity recognition and automatic summarization using HuggingFace's transformers library.

#### [![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://share.streamlit.io/mpolinsky/sju_final_project/main/streamlit_app.py)

**HuggingFace Spaces is currently experiencing difficulties performing requests from their containers.**
HuggingFace app link: https://huggingface.co/spaces/green/TopicDig

This application was created as the culmination of a semester of independent graduate research into NLP and transformers.

The app displays topics, the user chooses up to three, and the app spins up a topical digest scraped from the headlines.
This project makes heavy use of HuggingFace for NLP, and Gazpacho for web scraping.

Original repo for the earlier version of this app is located at https://github.com/mpolinsky/sju_final_project/