Skip to content

Latest commit

 

History

History
41 lines (33 loc) · 1.47 KB

README.md

File metadata and controls

41 lines (33 loc) · 1.47 KB
Raw

SNOOP Method: Faithfulness of Text Summarizations for Single Nucleotide Polymorphisms

This repository contains the implementation of the SNOOP method

File structure

▒   README.md
▒
+---data
▒       abstract.txt
▒       dataset.txt
▒       summary.txt
▒       text_with_embeddings.csv
▒
+---result
▒       cluster.png.jpg
▒       sbert_sim.csv
▒
+---src
        get_openai_embeddings.py
        main.py
        openai.py

  • main.py       > Implementation of Snoop method

  • dataset.txt    > the dataset consisting documents, references and out of domain texts

  • text_with_embeddings.csv    > contains the data (documents and references) and their embeddings obtained using openai embedding model

  • get_openai_embeddings.py   > python file to create openai embeddings

  • openai.py      > To implement Snoop using openai embeddings, use this file.

Read our paper

Paper

Citation

Maass, W., Agnes, C. K., Rahman, MR., Almeida, J. S. (2023). SNOOP Method: Faithfulness of Text Summarizations for Single Nucleotide Polymorphisms. 2nd Symposium on Human Partnership with Medical AI: Design, Operationalization, and Ethics at the Association for the Advancement of Artificial Intelligence (AAAI)Summer Symposium 2023, Singapore.