SciBERTSUM: Extractive Summarization for Scientific Documents
This work addresses the challenge of extractive summarization for long scientific papers, a domain-specific problem with incremental improvements over existing methods.
The authors tackled the problem of summarizing long scientific documents, which average over 500 sentences, by introducing SciBERTSUM, an extension of BERTSUM that incorporates section embeddings and sparse attention mechanisms, achieving superior ROUGE scores compared to baseline methods.
The summarization literature focuses on the summarization of news articles. The news articles in the CNN-DailyMail are relatively short documents with about 30 sentences per document on average. We introduce SciBERTSUM, our summarization framework designed for the summarization of long documents like scientific papers with more than 500 sentences. SciBERTSUM extends BERTSUM to long documents by 1) adding a section embedding layer to include section information in the sentence vector and 2) applying a sparse attention mechanism where each sentences will attend locally to nearby sentences and only a small number of sentences attend globally to all other sentences. We used slides generated by the authors of scientific papers as reference summaries since they contain the technical details from the paper. The results show the superiority of our model in terms of ROUGE scores.