Abstract
Unsupervised relation extraction (URE) extracts relations between named entities from raw text without manually-labelled data and existing knowledge bases (KBs). URE methods can be categorised into generative and discriminative approaches, which rely either on hand-crafted features or surface form. However, we demonstrate that by using only named entities to induce relation types, we can outperform existing methods on two popular datasets. We conduct a comparison and evaluation of our findings with other URE techniques, to ascertain the important features in URE. We conclude that entity types provide a strong inductive bias for URE.- Anthology ID:
- 2020.acl-main.669
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7498–7505
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.669
- DOI:
- 10.18653/v1/2020.acl-main.669
- Cite (ACL):
- Thy Thy Tran, Phong Le, and Sophia Ananiadou. 2020. Revisiting Unsupervised Relation Extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7498–7505, Online. Association for Computational Linguistics.
- Cite (Informal):
- Revisiting Unsupervised Relation Extraction (Tran et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2020.acl-main.669.pdf
- Code
- ttthy/ure
- Data
- New York Times Annotated Corpus