Improving Neural Relation Extraction with Positive and Unlabeled Learning

Authors

  • Zhengqiu He Soochow University
  • Wenliang Chen Soochow University
  • Yuyi Wang ETH Zurich
  • Wei Zhang Alibaba Group
  • Guanchun Wang Laiye Network Technology Co. LTD
  • Min Zhang Soochow University

DOI:

https://doi.org/10.1609/aaai.v34i05.6300

Abstract

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a given relation, and then positive and unlabeled bags are constructed. In contrast to most previous studies, which mainly use selected positive instances only, we make full use of unlabeled instances and propose two new representations for positive and unlabeled bags. These two representations are then combined in an appropriate way to make bag-level prediction. Experimental results on a widely used real-world dataset demonstrate that this new approach indeed achieves significant and consistent improvements as compared to several competitive baselines.

Downloads

Published

2020-04-03

How to Cite

He, Z., Chen, W., Wang, Y., Zhang, W., Wang, G., & Zhang, M. (2020). Improving Neural Relation Extraction with Positive and Unlabeled Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 34(05), 7927-7934. https://doi.org/10.1609/aaai.v34i05.6300

Issue

Section

AAAI Technical Track: Natural Language Processing