Semi-supervised Chinese Word Segmentation for CLP2012
He, Saike1; He, Nan2; Cen, Song-xiang1; Lu, Jun1
2012-12
会议名称The 2nd CIPS-SIGHAN Joint Conference on Chinese Language Processing (CLP-2012)
会议录名称The 2nd CIPS-SIGHAN Joint Conference on Chinese Language Processing (CLP-2012)
页码79- 84
会议日期2012-12-20 ~ 2012-12-21
会议地点Tianjin, China
摘要Chinese word segmentation (CWS) lays the essential foundation for Mandarin Chinese analysis. However, its performance is always limited by the identification of unknown words, especially for short text such as Microblog. While local context are helpless in handling unknown words, global context do manifest enough contextual information, and could be used to guide CWS process. Based on this motivation, in this paper, we report our attempt toward building an integrated model in semi-supervised manner. Considering the complexity of model, we design a strategy to manipulate global and local contextual information asynchronously. Though the coverage of unknown words by such integrated model is still small, official results from CLP2012 present promising result.
URL查看原文
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/10783
专题复杂系统管理与控制国家重点实验室_互联网大数据与信息安全
通讯作者He, Saike
作者单位1.State Key Laboratory of Management and Control for Complex Systems Institute of Automation
2.Nuance Software Technology (Beijing) Co., Ltd.
推荐引用方式
GB/T 7714
He, Saike,He, Nan,Cen, Song-xiang,et al. Semi-supervised Chinese Word Segmentation for CLP2012[C],2012:79- 84.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
W12-6315.pdf(208KB)会议论文 开放获取CC BY-NC-SA浏览 下载
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
[He, Saike]的文章
[He, Nan]的文章
[Cen, Song-xiang]的文章
百度学术
百度学术中相似的文章
[He, Saike]的文章
[He, Nan]的文章
[Cen, Song-xiang]的文章
必应学术
必应学术中相似的文章
[He, Saike]的文章
[He, Nan]的文章
[Cen, Song-xiang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: W12-6315.pdf
格式: Adobe PDF
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。