NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers
Lung-Hao Lee, Po-Han Chen, Yu-Xiang Zeng, Po-Lei Lee, Kuo-Kai Shyu
Abstract
This study describes the model design of the NCUEE-NLP system for the MEDIQA challenge at the BioNLP 2021 workshop. We use the PEGASUS transformers and fine-tune the downstream summarization task using our collected and processed datasets. A total of 22 teams participated in the consumer health question summarization task of MEDIQA 2021. Each participating team was allowed to submit a maximum of ten runs. Our best submission, achieving a ROUGE2-F1 score of 0.1597, ranked third among all 128 submissions.- Anthology ID:
- 2021.bionlp-1.30
- Volume:
- Proceedings of the 20th Workshop on Biomedical Language Processing
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Venue:
- BioNLP
- SIG:
- SIGBIOMED
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 268–272
- Language:
- URL:
- https://aclanthology.org/2021.bionlp-1.30
- DOI:
- 10.18653/v1/2021.bionlp-1.30
- Cite (ACL):
- Lung-Hao Lee, Po-Han Chen, Yu-Xiang Zeng, Po-Lei Lee, and Kuo-Kai Shyu. 2021. NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 268–272, Online. Association for Computational Linguistics.
- Cite (Informal):
- NCUEE-NLP at MEDIQA 2021: Health Question Summarization Using PEGASUS Transformers (Lee et al., BioNLP 2021)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2021.bionlp-1.30.pdf
- Data
- Medical Question Pairs