Abstract
In this paper we describe an evaluation of the potential of classical information extraction methods to extract drug-related attributes, including adverse drug events, and compare to more recently developed neural methods. We use the 2018 N2C2 shared task data as our gold standard data set for training. We train support vector machine classifiers to detect drug and drug attribute spans, and pair these detected entities as training instances for an SVM relation classifier, with both systems using standard features. We compare to baseline neural methods that use standard contextualized embedding representations for entity and relation extraction. The SVM-based system and a neural system obtain comparable results, with the SVM system doing better on concepts and the neural system performing better on relation extraction tasks. The neural system obtains surprisingly strong results compared to the system based on years of research in developing features for information extraction.- Anthology ID:
- W19-1903
- Volume:
- Proceedings of the 2nd Clinical Natural Language Processing Workshop
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota, USA
- Editors:
- Anna Rumshisky, Kirk Roberts, Steven Bethard, Tristan Naumann
- Venue:
- ClinicalNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 22–27
- Language:
- URL:
- https://aclanthology.org/W19-1903
- DOI:
- 10.18653/v1/W19-1903
- Cite (ACL):
- Timothy Miller, Alon Geva, and Dmitriy Dligach. 2019. Extracting Adverse Drug Event Information with Minimal Engineering. In Proceedings of the 2nd Clinical Natural Language Processing Workshop, pages 22–27, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- Extracting Adverse Drug Event Information with Minimal Engineering (Miller et al., ClinicalNLP 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/W19-1903.pdf