Reinforcement Learning for Relation Classification From Noisy Data

Existing relation classification methods that rely on distant supervision assume that a bag of sentences mentioning an entity pair are all describing a relation for the entity pair. Such methods, performing classification at the bag level, cannot identify the mapping between a relation and a sentence, and largely suffers from the noisy labeling problem. In this paper, we propose a novel model for relation classification at the sentence level from noisy data. The model has two modules: an instance selector and a relation classifier. The instance selector chooses high-quality sentences with reinforcement learning and feeds the selected sentences into the relation classifier, and the relation classifier makes sentencelevel prediction and provides rewards to the instance selector. The two modules are trained jointly to optimize the instance selection and relation classification processes. Experiment results show that our model can deal with the noise of data effectively and obtains better performance for relation classification at the sentence level.

Authors

• Jun Feng Hubei Key Laboratory of Distributed System Security, Hubei Engineering Research Center on Big Data Security, School of Cyber Science and Engineering, Huazhong University of Science and Technology
• Minlie Huang Tsinghua University, Tsinghua University The CoAI Group, DCST, Tsinghua University
• Li Zhao Shaanxi Normal University
• Yang Yang
• Xiaoyan Zhu Xi'an Jiaotong University

Keywords

No keywords are indexed for this paper.