NCUEE-NLP at BioLaySumm Task 2: Readability-Controlled Summarization of Biomedical Articles Using the PRIMERA Models

Chao Yi Chen, Jen Hao Yang, Lung Hao Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study describes the model design of the NCUEE-NLP system for BioLaySumm Task 2 at the BioNLP 2023 workshop. We separately fine-tune pretrained PRIMERA models to independently generate technical abstracts and lay summaries of biomedical articles. A total of seven evaluation metrics across three criteria were used to compare system performance. Our best submission was ranked first for relevance, second for readability, and fourth for factuality, tying first for overall performance.

Original languageEnglish
Title of host publicationBioNLP 2023 - BioNLP and BioNLP-ST, Proceedings of the Workshop
EditorsDina Demner-fushman, Sophia Ananiadou, Kevin Cohen
PublisherAssociation for Computational Linguistics (ACL)
Pages586-591
Number of pages6
ISBN (Electronic)9781959429852
StatePublished - 2023
Event22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, BioNLP 2023 - Toronto, Canada
Duration: 13 Jul 2023 → …

Publication series

NameProceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)0736-587X

Conference

Conference22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, BioNLP 2023
Country/TerritoryCanada
CityToronto
Period13/07/23 → …

Fingerprint

Dive into the research topics of 'NCUEE-NLP at BioLaySumm Task 2: Readability-Controlled Summarization of Biomedical Articles Using the PRIMERA Models'. Together they form a unique fingerprint.

Cite this