利用快速有效的特征模板选择算法和字符归一化增强基于crf的中文分词

Yulin Ren, Dehua Li
{"title":"利用快速有效的特征模板选择算法和字符归一化增强基于crf的中文分词","authors":"Yulin Ren, Dehua Li","doi":"10.1109/icomssc45026.2018.8941808","DOIUrl":null,"url":null,"abstract":"Conditional random fields (CRFs) are among the classic models for Chinese word segmentation (CWS). Deep neural networks (DNNs) have recently emerged as a research hotspot in natural language processing (NLP). However, studies exploring the use of DNN for CWS have not yielded significant gains over CRF models. Thus, developing CRFs for CWS remains a viable avenue for research. This paper proposes two methods to enhance CRF-based CWS. First, a rapid and effective sequential forward selection (SFS)-style method is utilized for feature template selection to balance search performance with search speed. Second, it describes a method for character normalization more robust than the traditional method. Incremental evaluations on the second SIGHAN bakeoff show that the two proposed methods reduce the error by 7.8%, and 10.6% respectively in terms of F-score. The final system achieved an F-score of 0.955 (AS), 0.955 (CITYU), 0.970 (MSR), and 0.952 (PKU), which is comparable to those of the best systems reported in the reference.","PeriodicalId":332213,"journal":{"name":"2018 International Computers, Signals and Systems Conference (ICOMSSC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhancing CRF-based Chinese Word Segmentation Using a Rapid and Effective Feature Template Selection Algorithm and Character Normalization\",\"authors\":\"Yulin Ren, Dehua Li\",\"doi\":\"10.1109/icomssc45026.2018.8941808\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Conditional random fields (CRFs) are among the classic models for Chinese word segmentation (CWS). Deep neural networks (DNNs) have recently emerged as a research hotspot in natural language processing (NLP). However, studies exploring the use of DNN for CWS have not yielded significant gains over CRF models. Thus, developing CRFs for CWS remains a viable avenue for research. This paper proposes two methods to enhance CRF-based CWS. First, a rapid and effective sequential forward selection (SFS)-style method is utilized for feature template selection to balance search performance with search speed. Second, it describes a method for character normalization more robust than the traditional method. Incremental evaluations on the second SIGHAN bakeoff show that the two proposed methods reduce the error by 7.8%, and 10.6% respectively in terms of F-score. The final system achieved an F-score of 0.955 (AS), 0.955 (CITYU), 0.970 (MSR), and 0.952 (PKU), which is comparable to those of the best systems reported in the reference.\",\"PeriodicalId\":332213,\"journal\":{\"name\":\"2018 International Computers, Signals and Systems Conference (ICOMSSC)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 International Computers, Signals and Systems Conference (ICOMSSC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/icomssc45026.2018.8941808\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 International Computers, Signals and Systems Conference (ICOMSSC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/icomssc45026.2018.8941808","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

条件随机场是中文分词的经典模型之一。深度神经网络(dnn)是近年来自然语言处理(NLP)领域的研究热点。然而,探索在CWS中使用DNN的研究并没有取得比CRF模型更大的进展。因此,开发CWS的CRFs仍然是一个可行的研究途径。本文提出了两种增强基于crf的CWS的方法。首先,采用快速有效的顺序前向选择(SFS)方法进行特征模板选择,以平衡搜索性能和搜索速度;其次,描述了一种比传统方法更具鲁棒性的字符规范化方法。对第二次sigan烘焙的增量评价表明,两种方法的F-score误差分别降低了7.8%和10.6%。最终系统的f得分分别为0.955 (AS)、0.955 (CITYU)、0.970 (MSR)和0.952 (PKU),与文献中报道的最佳系统相当。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Enhancing CRF-based Chinese Word Segmentation Using a Rapid and Effective Feature Template Selection Algorithm and Character Normalization
Conditional random fields (CRFs) are among the classic models for Chinese word segmentation (CWS). Deep neural networks (DNNs) have recently emerged as a research hotspot in natural language processing (NLP). However, studies exploring the use of DNN for CWS have not yielded significant gains over CRF models. Thus, developing CRFs for CWS remains a viable avenue for research. This paper proposes two methods to enhance CRF-based CWS. First, a rapid and effective sequential forward selection (SFS)-style method is utilized for feature template selection to balance search performance with search speed. Second, it describes a method for character normalization more robust than the traditional method. Incremental evaluations on the second SIGHAN bakeoff show that the two proposed methods reduce the error by 7.8%, and 10.6% respectively in terms of F-score. The final system achieved an F-score of 0.955 (AS), 0.955 (CITYU), 0.970 (MSR), and 0.952 (PKU), which is comparable to those of the best systems reported in the reference.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信