Spaces:
Runtime error
A newer version of the Gradio SDK is available:
5.4.0
title: Paper Highlights Extraction
emoji: π
colorFrom: gray
colorTo: yellow
sdk: gradio
sdk_version: 3.18.0
app_file: app.py
pinned: false
This demo shows in action the models we developed for the exam Deep Natural Language Processing during a.y. 2022-2023.
The model gets as input some sentences from a paper and a custom made context to extract the 3 best highlights.
The model we used for this task is based on BERT and THExt, for the implementation details refer to this repo on GitHub.
The input used in this Gradio app is different from the one used in the original implementation. We require to add at the beginning of the sentences the topic they refer to (CS, AI, BIO), in this way we can try to use the best model available. If not topic is received the defulat model is the one trained on the mix of the three topics. Refer to examples to understand how to write the input.