Abstract
We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative siblings according to the type tree. During prediction, we define a coarse-to-fine decoder that restricts viable candidates at each level of the ontology based on already predicted parent type(s). Our approach significantly outperform prior work on strict accuracy, demonstrating the effectiveness of our method.- Anthology ID:
- 2020.acl-main.749
- 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:
- 8465–8475
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.749
- DOI:
- 10.18653/v1/2020.acl-main.749
- Cite (ACL):
- Tongfei Chen, Yunmo Chen, and Benjamin Van Durme. 2020. Hierarchical Entity Typing via Multi-level Learning to Rank. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8465–8475, Online. Association for Computational Linguistics.
- Cite (Informal):
- Hierarchical Entity Typing via Multi-level Learning to Rank (Chen et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/landing_page/2020.acl-main.749.pdf
- Code
- ctongfei/hierarchical-typing
- Data
- FIGER