/Sequence-to-sequence-networks-for-multi-text-document-summarization

This repository explores the use of advanced sequence-to-sequence networks and transformer models, such as BERT, BART, PEGASUS, and T5, for summarizing multi-text documents in the medical domain. It leverages extensive datasets like CORD-19 and a Biomedical Abstracts dataset from Hugging Face to fine-tune these models.

Primary LanguageJupyter Notebook

Stargazers