English

Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix

Computation and Language 2018-05-16 v1

Abstract

Distant supervision significantly reduces human efforts in building training data for many classification tasks. While promising, this technique often introduces noise to the generated training data, which can severely affect the model performance. In this paper, we take a deep look at the application of distant supervision in relation extraction. We show that the dynamic transition matrix can effectively characterize the noise in the training data built by distant supervision. The transition matrix can be effectively trained using a novel curriculum learning based method without any direct supervision about the noise. We thoroughly evaluate our approach under a wide range of extraction scenarios. Experimental results show that our approach consistently improves the extraction results and outperforms the state-of-the-art in various evaluation scenarios.

Keywords

Cite

@article{arxiv.1705.03995,
  title  = {Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix},
  author = {Bingfeng Luo and Yansong Feng and Zheng Wang and Zhanxing Zhu and Songfang Huang and Rui Yan and Dongyan Zhao},
  journal= {arXiv preprint arXiv:1705.03995},
  year   = {2018}
}

Comments

10 pages, accepted by ACL 2017

R2 v1 2026-06-22T19:43:39.636Z