Research on Event Extraction Model Based on Semantic Features of Chinese Words

Authors

  • Shaowu Zhu College of Information and Network Security, People’s Public Security University of China, Beijing, China
  • Haichun Sun College of Information and Network Security, People’s Public Security University of China, Beijing, China
  • Hanying Jian College of Public Security Management, People’s Public Security University of China, Beijing, China

DOI:

https://doi.org/10.31577/cai_2022_6_1625

Keywords:

BERT, five strokes, Chinese glyph, event extraction, trigger extraction, named entity recognition

Abstract

Event Extraction (EE) is an important task in Natural Language Understanding (NLU). As the complexity of Chinese structure, Chinese EE is more difficult than English EE. According to the characteristics of Chinese, this paper designed a Semantic-GRU (Sem-GRU) model, which integrates Chinese word context semantics, Chinese word glyph semantics and Chinese word structure semantics. And this paper uses the model for Chinese Event Trigger Extraction (ETE) task. The experiment is compared in two tasks: ETE and Named Entity Recognition (NER). In ETE, the paper uses ACE 2005 Chinese event dataset to compare the existing research, the effect reaches 75.8 %. In NER, the paper uses MSRA dataset, which reaches 90.3 %, better than other models.

Downloads

Download data is not yet available.

Downloads

Published

2023-03-20

How to Cite

Zhu, S., Sun, H., & Jian, H. (2023). Research on Event Extraction Model Based on Semantic Features of Chinese Words. Computing and Informatics, 41(6), 1625–1647. https://doi.org/10.31577/cai_2022_6_1625