Dual Neural Network Fusion Model for Chinese Named Entity Recognition

Authors

Dandan Zhao^{1, 2,} , Jingxiang Cao^3, , Degen Huang^{1, *,} , Jiana Meng², Pan Zhang^2,

¹School of Computer Science and Technology, Dalian University of Technology, Dalian, China

²School of Computer Science and Engineering, Dalian Minzu University, Dalian, China

³School of Foreign Languages, Dalian Minzu University, Dalian, China

^*Corresponding author. Email: huangdg@dlut.edu.cn

DOI

10.2991/ijcis.d.201216.001How to use a DOI?

Keywords

Chinese named entity recognition; Dual neural network fusion; Bi-directional long-short-term memory; Self-attention mechanism; Dilated convolutional neural network

Abstract

Chinese named entity recognition (NER) has important effect on natural language processing (NLP) applications. This recognition task is complicated in its strong dependent-relation, missing delimiters in the text and insufficient feature representation in a single model. This paper thus proposes a dual neural network fusion model (DFM) to improve Chinese NER performance. We integrate the traditional bi-directional long-short-term memory (BiLSTM) structure and self-attention mechanism (ATT) with dilated convolutional neural network (DCNN) to better capture context information. Additionally, we exploit the Google's pretrained model named bi-directional encoder representations from transformers (BERT) as the embedding layer. The proposed model has the following merits: (1) a dual neural network architecture is proposed to enhance the robustness of extracted features. (2) An attention mechanism is fused into the dual neural network to extract implicit context representation information in Chinese NER. (3) Dilated convolutions are used to make a tradeoff between performance and executing speed. Experiments show that our proposed model exceeds the state-of-the-art Chinese NER methods.

Copyright

© 2021 The Authors. Published by Atlantis Press B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Dandan Zhao
AU  - Jingxiang Cao
AU  - Degen Huang
AU  - Jiana Meng
AU  - Pan Zhang
PY  - 2020
DA  - 2020/12/24
TI  - Dual Neural Network Fusion Model for Chinese Named Entity Recognition
JO  - International Journal of Computational Intelligence Systems
SP  - 471
EP  - 481
VL  - 14
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.201216.001
DO  - 10.2991/ijcis.d.201216.001
ID  - Zhao2020
ER  -