Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix
Bingfeng Luo, Yansong Feng, Zheng Wang, Zhanxing Zhu, Songfang Huang, Rui Yan, Dongyan Zhao
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.- Anthology ID:
- P17-1040
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 430–439
- Language:
- URL:
- https://aclanthology.org/P17-1040
- DOI:
- 10.18653/v1/P17-1040
- Cite (ACL):
- Bingfeng Luo, Yansong Feng, Zheng Wang, Zhanxing Zhu, Songfang Huang, Rui Yan, and Dongyan Zhao. 2017. Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 430–439, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Learning with Noise: Enhance Distantly Supervised Relation Extraction with Dynamic Transition Matrix (Luo et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/P17-1040.pdf