Abstract
Biomedical event extraction from natural text is a challenging task as it searches for complex and often nested structures describing specific relationships between multiple molecular entities, such as genes, proteins, or cellular components. It usually is implemented by a complex pipeline of individual tools to solve the different relation extraction subtasks. We present an alternative approach where the detection of relationships between entities is described uniformly as questions, which are iteratively answered by a question answering (QA) system based on the domain-specific language model SciBERT. This model outperforms two strong baselines in two biomedical event extraction corpora in a Knowledge Base Population setting, and also achieves competitive performance in BioNLP challenge evaluation settings.- Anthology ID:
- 2020.louhi-1.10
- Volume:
- Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Eben Holderness, Antonio Jimeno Yepes, Alberto Lavelli, Anne-Lyse Minard, James Pustejovsky, Fabio Rinaldi
- Venue:
- Louhi
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 88–96
- Language:
- URL:
- https://aclanthology.org/2020.louhi-1.10
- DOI:
- 10.18653/v1/2020.louhi-1.10
- Cite (ACL):
- Xing David Wang, Leon Weber, and Ulf Leser. 2020. Biomedical Event Extraction as Multi-turn Question Answering. In Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis, pages 88–96, Online. Association for Computational Linguistics.
- Cite (Informal):
- Biomedical Event Extraction as Multi-turn Question Answering (Wang et al., Louhi 2020)
- PDF:
- https://preview.aclanthology.org/landing_page/2020.louhi-1.10.pdf
- Code
- wangxii/bio_event_qa