Abstract
Medical question summarization is an important but difficult task, where the input is often complex and erroneous while annotated data is expensive to acquire. We report our participation in the MEDIQA 2021 question summarization task in which we are required to address these challenges. We start from pre-trained conditional generative language models, use knowledge bases to help correct input errors, and rerank single system outputs to boost coverage. Experimental results show significant improvement in string-based metrics.- Anthology ID:
- 2021.bionlp-1.12
- Volume:
- Proceedings of the 20th Workshop on Biomedical Language Processing
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
- Venue:
- BioNLP
- SIG:
- SIGBIOMED
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 112–118
- Language:
- URL:
- https://aclanthology.org/2021.bionlp-1.12
- DOI:
- 10.18653/v1/2021.bionlp-1.12
- Cite (ACL):
- Yifan He, Mosha Chen, and Songfang Huang. 2021. damo_nlp at MEDIQA 2021: Knowledge-based Preprocessing and Coverage-oriented Reranking for Medical Question Summarization. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 112–118, Online. Association for Computational Linguistics.
- Cite (Informal):
- damo_nlp at MEDIQA 2021: Knowledge-based Preprocessing and Coverage-oriented Reranking for Medical Question Summarization (He et al., BioNLP 2021)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2021.bionlp-1.12.pdf
- Data
- MeQSum