English

Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision

Computation and Language 2023-02-13 v2

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

Keywords

Cite

@article{arxiv.2205.08770,
  title  = {Relation Extraction with Weighted Contrastive Pre-training on Distant Supervision},
  author = {Zhen Wan and Fei Cheng and Qianying Liu and Zhuoyuan Mao and Haiyue Song and Sadao Kurohashi},
  journal= {arXiv preprint arXiv:2205.08770},
  year   = {2023}
}

Comments

EACL 2023 (Findings)

R2 v1 2026-06-24T11:20:47.040Z