Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5182–5192 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 5182 Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks Hongyu Lin1,3, Yaojie Lu1,3, Xianpei Han1,2,∗, Le Sun1,2 1Chinese Information Processing Laboratory 2State Key Laboratory of Computer Science Institute of Software, Chinese Academy of Sciences, Beijing, China 3University of Chinese Academy of Sciences, Beijing, China {hongyu2016,yaojie2017,xianpei,sunle}@iscas.ac.cn Abstract Sequential labeling-based NER approaches re- strict each word belonging to at most one entity mention, which will face a serious problem when recognizing nested entity men- tions. In this paper, we propose to resolve this problem by modeling and leveraging the head-driven phrase structures of entity men- tions, i.e., although a mention can nest other mentions, they will not share the same head word. Specifically, we propose Anchor-Region Networks (ARNs), a sequence-to-nuggets ar- chitecture for nested mention detection. ARNs first identify anchor words (i.e., possible head words) of all mentions, and then recognize the mention boundaries for each anchor word by exploiting regular phrase structures. Further- more, we also design Bag Loss, an objective function which can train ARNs in an end-to- end manner without using any anchor word annotation. Experiments show that ARNs achieve the state-of-the-art performance on three standard nested entity mention detection benchmarks. 1 Introduction Named entity recognition (NER), or more gen- erally entity mention detection1, aims to identify text spans pertaining to specific entity types such as Person, Organization and Location. NER is a fundamental task of information extraction which enables many downstream NLP applica- tions, such as relation extraction (GuoDong et al., 2005; Mintz et al., 2009), event extraction (Ji and Grishman, 2008; Li et al., 2013) and machine reading comprehension (Rajpurkar et al., 2016; Wang et al., 2016). Previous approaches (Zhou and Su, 2002; Chieu and Ng, 2002; Bender et al., 2003; Settles, 2004; ∗Corresponding author. 1In entity mention detection, a mention can be either a named, nominal or pronominal reference of an entity (Katiyar and Cardie, 2018). The minister of the department of education convened a meeting. ORG PER Figure 1: An example of nested entity mentions. Due to the nested structure, “the”,“department”,“of” and “education” belong to both PER and ORG mentions. Lample et al., 2016) commonly regard NER as a sequential labeling task, which generate label sequence for each sentence by assigning one la- bel to each token. These approaches commonly restrict each token belonging to at most one entity mention and, unfortunately, will face a serious problem when recognizing nested entity mentions, where one token may belong to multiple mentions. For example in Figure 1, an Organization entity mention “the department of education” is nested in another Person entity mention “the minister of the department of education”. Nested entity mentions are very common. For instance, in the well-known ACE2005 and RichERE datasets, more than 20% of entity mentions are nested in other mentions. Therefore, it is critical to consider nested mentions for real-world applications and downstream tasks. In …

Content truncated to 500 words