Hierarchical Region Learning for Nested Named Entity Recognition

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4788–4793 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 4788 Hierarchical Region Learning for Nested Named Entity Recognition Xinwei Long1,2, Shuzi Niu1∗and Yucheng Li1 1Institute of Software, Chinese Academy of Sciences, Beijing, China 2University of Chinese Academy of Sciences, Beijing, China longxinwei19@mails.ucas.ac.cn, {shuzi, yucheng}@iscas.ac.cn Abstract Named Entity Recognition (NER) is deeply explored and widely used in various tasks. Usually, some entity mentions are nested in other entities, which leads to the nested NER problem. Leading region based models face both the efficiency and effectiveness challenge due to the high subsequence enumeration com- plexity. To tackle these challenges, we pro- pose a hierarchical region learning framework to automatically generate a tree hierarchy of candidate regions with nearly linear complex- ity and incorporate structure information into the region representation for better classifi- cation. Experiments on benchmark datasets ACE-2005, GENIA and JNLPBA demonstrate competitive or better results than state-of-the- art baselines. 1 Introduction As a fundamental information extraction task, Named Entity Recognition (NER) is widely used in various downstream tasks, such as entity linking and entity search. Most studies assigns a label to each token of the sequence for the flat NER prob- lem (Lample et al., 2016). However, it is common that entities are embedded in other entities in many domains (Kim et al., 2003; Ringland et al., 2019). Example from ACE-2005 dataset shown in Fig. 1 illustrates that the top-level PER entity includes a nested entity with ORG label. How to recognize all entities recursively from innermost to outermost is referred to as the Nested NER problem. ���������������������������������������������������������� ��� ��� �� �� �� �� �� �� �� �� Figure 1: Illustration of nested entities and constituent parsing tree ∗ Corresponding author. Existing approaches mainly solve the nested NER problem by classifying all candidate sub- sequences (a.k.a regions). The key to region based methods lies in candidate region detection. one kind is the brute force method (Sohrab and Miwa, 2018) to enumerate all possible O(n2) sub- sequences for each sentence with n words. The other kind (Zheng et al., 2019) is to generate and classify candidate regions in a two-stage paradigm, often leading to cascaded errors. Thus region based methods face efficiency and effectiveness challenges. To tackle these challenges, we propose a Hierarchical Region learning framework, referred to as HiRe. First, inspired by constituent parsing tree as the top of Fig. 1 and its neural syntactic distance (Shen et al., 2018), we introduce the co- herence measure between adjacent regions. Then we generate a region tree for each sentence by merg- ing two adjacent regions recursively based on this region coherence measure in a bottom-up manner. Finally, hierarchical regions are classified based on the boundary and merging word representation. We train the hierarchical region generation and classifi- cation tasks simultaneously. Experimental results on three benchmark datasets ACE-2005, GENIA and JNLPBA demon- strate that HiRe shows the competitive or better performance than baselines. HiRe generates only O(n) candidate regions about 77.9% …

Content truncated to 500 words