UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
Wei Tang, Benfeng Xu, Yuyue Zhao, Zhendong Mao, Yifeng Liu, Yong Liao, Haiyong Xie
Abstract
Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations. Existing works suffer from 1) heterogeneous representations of entities and relations, and 2) heterogeneous modeling of entity-entity interactions and entity-relation interactions. Therefore, the rich correlations are not fully exploited by existing works. In this paper, we propose UniRel to address these challenges. Specifically, we unify the representations of entities and relations by jointly encoding them within a concatenated natural language sequence, and unify the modeling of interactions with a proposed Interaction Map, which is built upon the off-the-shelf self-attention mechanism within any Transformer block. With comprehensive experiments on two popular relational triple extraction datasets, we demonstrate that UniRel is more effective and computationally efficient. The source code is available at https://github.com/wtangdev/UniRel.- Anthology ID:
- 2022.emnlp-main.477
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Editors:
- Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7087–7099
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.477
- DOI:
- 10.18653/v1/2022.emnlp-main.477
- Cite (ACL):
- Wei Tang, Benfeng Xu, Yuyue Zhao, Zhendong Mao, Yifeng Liu, Yong Liao, and Haiyong Xie. 2022. UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7087–7099, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction (Tang et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.emnlp-main.477.pdf