Toward Recognizing More Entity Types in NER: An Efficient Implementation using Only Entity Lexicons

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 678–688 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 678 Toward Recognizing More Entity Types in NER: An Efficient Implementation using Only Entity Lexicons Minlong Peng1, Ruotian Ma1, Qi Zhang1, Lujun Zhao2, Mengxi Wei2, Changlong Sun2, Xuanjing Huang1 School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China1 Alibaba Group, Hangzhou, China2 {mlpeng16,rtma19,qz,xjhuang}@fudan.edu.cn1 {lujun.zlj,cangqing.wmx}@alibaba-inc.com2, changlong.scl@taobao.com2 Abstract In this work, we explore the way to quickly adjust an existing named entity recognition (NER) system to make it capable of recogniz- ing entity types not defined in the system. As an illustrative example, consider the case that a NER system has been built to recognize person and organization names, and now it requires to additionally recognize job titles. Such a situa- tion is common in the industrial areas, where the entity types required to recognize vary a lot in different products and keep changing. To avoid laborious data labeling and achieve fast adaptation, we propose to adjust the existing NER system using the previously labeled data and entity lexicons of the newly introduced entity types. We formulate such a task as a partially supervised learning problem and accordingly propose an effective algorithm to solve the problem. Comprehensive experi- mental studies on several public NER datasets validate the effectiveness of our method. 1 Introduction Named Entity Recognition (NER) is a type of information extraction task that seeks to identify entity names from unstructured text and categorize them into a predefined list of types. It plays an important role in many downstream tasks such as knowledge base construction (Riedel et al., 2013; Shen et al., 2012), machine translation (Babych and Hartley, 2003), and search (Zhu et al., 2005), etc. In this field, the supervised methods, ranging from the conventional graph models (McCallum et al., 2000; Malouf, 2002; McCallum and Li, 2003; Settles, 2004) to the dominant deep neural methods (Collobert et al., 2011; Huang et al., 2015; Lample et al., 2016; Gridach, 2017; Liu et al., 2018; Zhang and Yang, 2018; Jiang et al., 2019; Gui et al., 2019), have achieved great success. However, these supervised methods usually require large scale labeled data to achieve good performance, while the annotation of NER data is often laborious and time-consuming. In the real world, there are many, or more strictly speaking, infinite numbers of entity types. It is impossible for a NER system to cover all entity types (Ling and Weld, 2012; Mai et al., 2018). Therefore, in the industrial area, it often happens that some entity types required to recognize by the clients are not defined in the previously designed NER system. In such a case, we need to quickly adjust the existing NER system to make it capable of recognizing the new entity types required by the clients. In this literature, we refer to the existing NER system as the source system, and refer to the adjusted system as the target system. The NER tasks defined in …

Content truncated to 500 words