An Extractive-Abstractive Approach for Multi-document Summarization of Scientific Articles for Literature Review

Kartik Shinde, Trinita Roy, Tirthankar Ghosal


Abstract
Research in the biomedical domain is con- stantly challenged by its large amount of ever- evolving textual information. Biomedical re- searchers are usually required to conduct a lit- erature review before any medical interven- tion to assess the effectiveness of the con- cerned research. However, the process is time- consuming, and therefore, automation to some extent would help reduce the accompanying information overload. Multi-document sum- marization of scientific articles for literature reviews is one approximation of such automa- tion. Here in this paper, we describe our pipelined approach for the aforementioned task. We design a BERT-based extractive method followed by a BigBird PEGASUS-based ab- stractive pipeline for generating literature re- view summaries from the abstracts of biomedi- cal trial reports as part of the Multi-document Summarization for Literature Review (MSLR) shared task1 in the Scholarly Document Pro- cessing (SDP) workshop 20222. Our proposed model achieves the best performance on the MSLR-Cochrane leaderboard3 on majority of the evaluation metrics. Human scrutiny of our automatically generated summaries indicates that our approach is promising to yield readable multi-article summaries for conducting such lit- erature reviews.
Anthology ID:
2022.sdp-1.25
Volume:
Proceedings of the Third Workshop on Scholarly Document Processing
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
sdp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
204–209
Language:
URL:
https://aclanthology.org/2022.sdp-1.25
DOI:
Bibkey:
Cite (ACL):
Kartik Shinde, Trinita Roy, and Tirthankar Ghosal. 2022. An Extractive-Abstractive Approach for Multi-document Summarization of Scientific Articles for Literature Review. In Proceedings of the Third Workshop on Scholarly Document Processing, pages 204–209, Gyeongju, Republic of Korea. Association for Computational Linguistics.
Cite (Informal):
An Extractive-Abstractive Approach for Multi-document Summarization of Scientific Articles for Literature Review (Shinde et al., sdp 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.sdp-1.25.pdf
Code
 allenai/mslr-shared-task