Simplify the Usage of Lexicon in Chinese NER

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5951–5960 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 5951 Simplify the Usage of Lexicon in Chinese NER Ruotian Ma1∗, Minlong Peng1∗, Qi Zhang1,3, Zhongyu Wei2,3, Xuanjing Huang1 1Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University 2School of Data Science, Fudan University 3Research Institute of Intelligent and Complex Systems, Fudan University {rtma19,mlpeng16,qz,zywei,xjhuang}@fudan.edu.cn Abstract Recently, many works have tried to augment the performance of Chinese named entity recognition (NER) using word lexicons. As a representative, Lattice-LSTM (Zhang and Yang, 2018) has achieved new benchmark results on several public Chinese NER datasets. However, Lattice-LSTM has a complex model architecture. This limits its application in many industrial areas where real-time NER responses are needed. In this work, we propose a simple but effective method for incorporating the word lexicon into the character representations. This method avoids designing a complicated sequence mod- eling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information. Experimental studies on four benchmark Chinese NER datasets show that our method achieves an inference speed up to 6.15 times faster than those of state-of- the-art methods, along with a better perfor- mance. The experimental results also show that the proposed method can be easily incor- porated with pre-trained models like BERT. 1 1 Introduction Named Entity Recognition (NER) is concerned with the identification of named entities, such as persons, locations, and organizations, in un- structured text. NER plays an important role in many downstream tasks, including knowledge base construction (Riedel et al., 2013), information retrieval (Chen et al., 2015), and question answer- ing (Diefenbach et al., 2018). In languages where words are naturally separated (e.g., English), NER has been conventionally formulated as a sequence ∗Equal contribution. 1The source code of this paper is publicly available at https://github.com/v-mipeng/ LexiconAugmentedNER. labeling problem, and the state-of-the-art results have been achieved using neural-network-based models (Huang et al., 2015; Chiu and Nichols, 2016; Liu et al., 2018). Compared with NER in English, Chinese NER is more difficult since sentences in Chinese are not naturally segmented. Thus, a common practice for Chinese NER is to first perform word segmentation using an existing CWS system and then apply a word-level sequence labeling model to the seg- mented sentence (Yang et al., 2016; He and Sun, 2017b). However, it is inevitable that the CWS system will incorrectly segment query sentences. This will result in errors in the detection of entity boundary and the prediction of entity category in NER. Therefore, some approaches resort to performing Chinese NER directly at the character level, which has been empirically proven to be effective (He and Wang, 2008; Liu et al., 2010; Li et al., 2014; Liu et al., 2019; Sui et al., 2019; Gui et al., 2019b; Ding et al., 2019). A drawback of the purely character-based NER method is that the word information is not fully ex- ploited. …

Content truncated to 500 words