Reinforcement Learning for Named Entity Recognition from Noisy Data

摘要：

　　Named entity recognition(NER)is an important task in nat-ural language processing,and is often formalized as a sequence labeling problem.Deep learning becomes the state-of-the-art approach for NER,but the lack of high-quality labeled data remains the bottleneck for model performance.To solve the problem,we employ the distant supervision technique to obtain noisy labeled data,and propose a novel model based on reinforcement learning to revise the wrong labels and distill high-quality data for learning.Specifically,our model consists of two mod-ules,a Tag Modifier and a Tag Predictor.The Tag Modifier corrects the wrong tags with reinforcement learning and feeds the corrected tags into the Tag Predictor.The Tag Predictor makes the sentence-level predic-tion and returns rewards to the Tag Modifier.Two modules are trained jointly to optimize tag correction and prediction processes.Experiment results show that our model can effectively deal with noises with a small number of correctly labeled data and thus outperform state-of-the-art baselines.

关键词： Named entity recognition Noisy data Reinforcement learning

作者: Jing Wan Haoming Li Lei Hou Juaizi Li

作者单位: Beijing University of Chemical Technology,Beijing,China Department of Computer Science and Technology,BNRist,Beijing,China;KIRC,Institute for Artificial Int

会议类型: 国际会议

会议名称: 9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)

会议地点: 郑州

会议语种:英文

页码: 333-345

在线出版日期: 2020-10-14（万方平台首次上网日期，不代表论文的发表时间）