Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision
Zhen Wan, Fei Cheng, Qianying Liu, Zhuoyuan Mao, Haiyue Song, Sadao Kurohashi
Abstract
Contrastive pre-training on distant supervision has shown remarkable effectiveness in improving supervised relation extraction tasks. However, the existing methods ignore the intrinsic noise of distant supervision during the pre-training stage. In this paper, we propose a weighted contrastive learning method by leveraging the supervised data to estimate the reliability of pre-training instances and explicitly reduce the effect of noise.Experimental results on three supervised datasets demonstrate the advantages of our proposed weighted contrastive learning approach compared to two state-of-the-art non-weighted baselines.Our code and models are available at: https://github.com/YukinoWan/WCL.- Anthology ID:
- 2023.findings-eacl.195
- Volume:
- Findings of the Association for Computational Linguistics: EACL 2023
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2580–2585
- Language:
- URL:
- https://aclanthology.org/2023.findings-eacl.195
- DOI:
- Cite (ACL):
- Zhen Wan, Fei Cheng, Qianying Liu, Zhuoyuan Mao, Haiyue Song, and Sadao Kurohashi. 2023. Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision. In Findings of the Association for Computational Linguistics: EACL 2023, pages 2580–2585, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision (Wan et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2023.findings-eacl.195.pdf