Bipartite Flat-Graph Network for Nested Named Entity Recognition

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6408–6418 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 6408 Bipartite Flat-Graph Network for Nested Named Entity Recognition Ying Luo and Hai Zhao∗ Department of Computer Science and Engineering, Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering, Shanghai Jiao Tong University, Shanghai, China MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China kingln@sjtu.edu.cn, zhaohai@cs.sjtu.edu.cn Abstract In this paper, we propose a novel bipartite flat- graph network (BiFlaG) for nested named en- tity recognition (NER), which contains two subgraph modules: a flat NER module for out- ermost entities and a graph module for all the entities located in inner layers. Bidirectional LSTM (BiLSTM) and graph convolutional net- work (GCN) are adopted to jointly learn flat entities and their inner dependencies. Differ- ent from previous models, which only consider the unidirectional delivery of information from innermost layers to outer ones (or outside-to- inside), our model effectively captures the bidi- rectional interaction between them. We first use the entities recognized by the flat NER module to construct an entity graph, which is fed to the next graph module. The richer representation learned from graph module car- ries the dependencies of inner entities and can be exploited to improve outermost entity pre- dictions. Experimental results on three stan- dard nested NER datasets demonstrate that our BiFlaG outperforms previous state-of-the-art models. 1 Introduction Named entity recognition (NER) aims to identify words or phrases that contain the names of pre- defined categories like location, organization or medical codes. Nested NER further deals with entities that can be nested with each other, such as the United States and third president of the United States shown in Figure 1, such phenomenon is quite common in natural language processing (NLP). NER is commonly regarded as a sequence label- ing task (Lample et al., 2016; Ma and Hovy, 2016; ∗ Corresponding author. This paper was partially sup- ported by National Key Research and Development Program of China (No. 2017YFB0304100), Key Projects of Na- tional Natural Science Foundation of China (U1836222 and 61733011), Huawei-SJTU long term AI project, Cutting-edge Machine reading comprehension and language model. V1 V4 V2 V5 V3 Thomas Jefferson, third president of the United States { { { PER GPE V0 V5 V7 Entity Graph GPE PER PER V7 V6 V2 Figure 1: An example of nested named entity mentions. Solid lines connect the starting and ending indices of inner nested entities. Peters et al., 2017). These approaches only work for non-nested entities (or flat entities), but neglect nested entities. There have been efforts to deal with the nested structure. Ju et al. 2018 introduced a layered sequence labeling model to first recog- nize innermost entities, and then feed them into the next layer to extract outer entities. However, this model suffers from obvious error propagation. The wrong entities extracted by the previous layer will affect the performance of the …

Content truncated to 500 words