LED down the rabbit hole: Exploring the potential of global attention for biomedical multi-document summarisation

Authors

Yulia Otmakhova, The University of Melbourne, Australia
Hung Thinh Truong, The University of Melbourne, Australia
Timothy Baldwin, The University of Melbourne, Australia & Mohamed bin Zayed University of Artificial IntelligenceFollow
Trevor Cohn, The University of Melbourne, Australia
Karin Verspoor, The University of Melbourne, Australia & RMIT University, Australia
Jey Han Lau, The University of Melbourne, Australia

Document Type

Article

Publication Title

arXiv

Abstract

In this paper we report on our submission to the Multidocument Summarisation for Literature Review (MSLR) shared task. Specifically, we adapt PRIMERA (Xiao et al., 2022) to the biomedical domain by placing global attention on important biomedical entities in several ways. We analyse the outputs of the 23 resulting models, and report patterns in the results related to the presence of additional global attention, number of training steps, and the input configuration. © 2022, CC BY-SA.

DOI

10.48550/arXiv.2209.08698

Publication Date

9-19-2022

Keywords

Biomedical domain, Literature reviews, Multi documents summarization

Comments

Preprint: arXiv

Archived with thanks to arXiv

Preprint License: CC by SA 4.0

Uploaded 12 October 2022

Recommended Citation

Y. Otmakhova, H.T. Truong, T. Baldwin, T. Cohn, K. Verspoor, and J.H. Lau, "LED down the rabbit hole: Exploring the potential of global attention for biomedical multi-document summarisation", 2022, doi:10.48550/arXiv.2209.08698