XJIPC OpenIR  > 多语种信息技术研究室
Discriminative learning with natural annotations: Word segmentation as a case study
JiangWenbin; SunMeng; ; , Yajuan; YangYating; LiuQun
2013
会议名称51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
页码761-769
会议日期August 4, 2013 - August 9, 2013
会议地点Sofia, Bulgaria
出版地Association for Computational Linguistics (ACL)
摘要

Structural information in web text provides natural annotations for NLP problems such as word segmentation and parsing. In this paper we propose a discriminative learning algorithm to take advantage of the linguistic knowledge in large amounts of natural annotations on the Internet. It utilizes the Internet as an external corpus with massive (although slight and sparse) natural annotations, and enables a classifier to evolve on the large-scaled and real-time updated web text. With Chinese word segmentation as a case study, experiments show that the segmenter enhanced with the Chinese wikipedia achieves significant improvement on a series of testing sets from different domains, even with a single classifier and local features.

收录类别EI
文献类型会议论文
条目标识符http://ir.xjipc.cas.cn/handle/365002/3616
专题多语种信息技术研究室
作者单位Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, China
推荐引用方式
GB/T 7714
JiangWenbin,SunMeng,Lü,et al. Discriminative learning with natural annotations: Word segmentation as a case study[C]. Association for Computational Linguistics (ACL),2013:761-769.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Discriminative Learn(241KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[JiangWenbin]的文章
[SunMeng]的文章
[Lü]的文章
百度学术
百度学术中相似的文章
[JiangWenbin]的文章
[SunMeng]的文章
[Lü]的文章
必应学术
必应学术中相似的文章
[JiangWenbin]的文章
[SunMeng]的文章
[Lü]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Discriminative Learning with Natural Annotations Word Segmentation as a Case Study.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。