ZH-NER: Chinese Named Entity Recognition with Adversarial Multi-task Learning and Self-Attentions

Abstract

NER is challenging because of the semantic ambiguities in academic literature, especially for non-Latin languages. Besides, recognizing Chinese named entities needs to consider word boundary information, as words contained in Chinese texts are not separated with spaces. Leveraging word boundary information could help to determine entity boundaries and thus improve entity recognition performance. In this paper, we propose to combine word boundary information and semantic information for named entity recognition based on multi-task adversarial learning. We learn common shared boundary information of entities from multiple kinds of tasks, including Chinese word segmentation (CWS), part-of-speech (POS) tagging and entity recognition, with adversarial learning. We learn task-specific semantic information of words from these tasks, and combine the learned boundary information with the semantic information to improve entity recognition, with multi-task learning. We conduct extensive experiments to demonstrate that our model achieves considerable performance improvements.