Abstract
Relation extraction (RE) aims to label relations between groups of marked entities in raw text. Most current RE models learn context-aware representations of the target entities that are then used to establish relation between them. This works well for intra-sentence RE, and we call them first-order relations. However, this methodology can sometimes fail to capture complex and long dependencies. To address this, we hypothesize that at times the target entities can be connected via a context token. We refer to such indirect relations as second-order relations, and describe an efficient implementation for computing them. These second-order relation scores are then combined with first-order relation scores to obtain final relation scores. Our empirical results show that the proposed method leads to state-of-the-art performance over two biomedical datasets.- Anthology ID:
- N19-1147
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1442–1447
- Language:
- URL:
- https://aclanthology.org/N19-1147
- DOI:
- 10.18653/v1/N19-1147
- Cite (ACL):
- Gaurav Singh and Parminder Bhatia. 2019. Relation Extraction using Explicit Context Conditioning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1442–1447, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Relation Extraction using Explicit Context Conditioning (Singh & Bhatia, NAACL 2019)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/N19-1147.pdf