NSL OpenIR  > 中国科学院成都文献情报中心  > 区域发展咨询部  > 信息服务部
A Mixed Semantic Features Model for Chinese NER with Characters and Words
Chang, Ning1; Zhong, Jiang1,2; Li, Qing1; Zhu, Jiang3
2020-04
Conference Name42nd European Conference on IR Research, ECIR 2020
Source PublicationLecture Notes in Computer Science, v 12035 LNCS,  2020, Advances in Information Retrieval - 42nd European Conference on IR Research, ECIR 2020, Proceedings
Issuev 12035
Pages356-368
Conference DateApril 14 - 17, 2020
Conference PlaceLisbon, Portugal
PublisherSpringer
Abstract

Named Entity Recognition (NER) is an essential part of many natural language processing (NLP) tasks. The existing Chinese NER methods are mostly based on word segmentation, or use the character sequences as input. However, using a single granularity representation would suffer from the problems of out-of-vocabulary and word segmentation errors, and the semantic content is relatively simple. In this paper, we introduce the self-attention mechanism into the BiLSTM-CRF neural network structure for Chinese named entity recognition with two embedding. Different from other models, our method combines character and word features at the sequence level, and the attention mechanism computes similarity on the total sequence consisted of characters and words. The character semantic information and the structure of words work together to improve the accuracy of word boundary segmentation and solve the problem of long-phrase combination. We validate our model on MSRA andWeibo corpora, and experiments demonstrate that our model can significantly improve the performance of the Chinese NER task.

KeywordChinese Named Entity Recognition Self-attention Mixed Semantic Feature Entity Boundary Segmentation
MOST Discipline Catalogue管理学::图书情报与档案管理
DOI10.1007/978-3-030-45439-5_24
URL查看原文
Indexed ByEI
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.las.ac.cn/handle/12502/11771
Collection中国科学院成都文献情报中心_区域发展咨询部_信息服务部
Corresponding AuthorZhong, Jiang
Affiliation1.Chongqing University, Chongqing 400044, People’s Republic of China
2.Key Laboratory of Dependable Service Computing in Cyber Physical Society, Chongqing University, Chongqing 400044, People’s Republic of China
3.Chengdu Library and Information Center, Chinese Academy of Sciences, Chengdu 610041, People’s Republic of China
First Author Affilication中国科学院文献情报中心
Corresponding Author Affilication中国科学院文献情报中心
Recommended Citation
GB/T 7714
Chang, Ning,Zhong, Jiang,Li, Qing,et al. A Mixed Semantic Features Model for Chinese NER with Characters and Words[C]:Springer,2020:356-368.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chang, Ning]'s Articles
[Zhong, Jiang]'s Articles
[Li, Qing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chang, Ning]'s Articles
[Zhong, Jiang]'s Articles
[Li, Qing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chang, Ning]'s Articles
[Zhong, Jiang]'s Articles
[Li, Qing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.