A Korean named entity recognition method using Bi-LSTM-CRF and masked self-attention. (January 2021)

• Record Type: Journal Article
• Authors: Jin, Guozhe; Yu, Zhezhou
• Is Part Of: Computer speech & language. Volume 65(2021)
• Publication Date: 2021-01
• Subjects: Korean -- named entity recognition -- auxiliary tasks -- Bi-LSTM-CRF; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101134
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: An independent morpheme-level NE tagger is introduced to our model to enhance the syllable features of the morpheme. A masked self-attention network is proposed to enhance the context feature of morpheme. The proposed model outperforms previous state-of-the-art models. Abstract: Named entity recognition (NER) is a fundamental task in natural language processing. The existing Korean NER methods use the Korean morpheme, syllable sequence, and part-of-speech as features, and use a sequence labeling model to tackle this problem. In Korean, on one hand, morpheme itself contains strong indicative information of named entity (especially for time and person). On the other hand, the context of the target morpheme plays an important role in recognizing the named entity(NE) tag of the target morpheme. To make full use of these two features, we propose two auxiliary tasks. One of them is the morpheme-level NE tagging task which will capture the NE feature of syllable sequence composing morpheme. The other one is the context-based NE tagging task which aims to capture the context feature of target morpheme through the masked self-attention network. These two tasks are jointly trained with Bi-LSTM-CRF NER Tagger. The experimental results on Klpexpo 2016 corpus and Naver NLP Challenge 2018 corpus show that our model outperforms the strong baseline systems and achieves the state of the art.