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.
Cite
CITATION STYLE
Chen, C. Y., Yang, J. H., & Lee, L. H. (2023). NCUEE-NLP at BioLaySumm Task 2: Readability-Controlled Summarization of Biomedical Articles Using the PRIMERA Models. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp. 586–591). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.bionlp-1.62
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.