CSpace  > 中国科学院计算技术研究所期刊论文  > 英文
Parsing the Penn Chinese Treebank with semantic knowledge
Xiong, DY; Li, SL; Liu, Q; Lin, SX; Qian, YL
2005
发表期刊NATURAL LANGUAGE PROCESSING - IJCNLP 2005, PROCEEDINGS
ISSN0302-9743
卷号3651页码:70-81
摘要We build a class-based selection preference sub-model to incorporate external semantic knowledge from two Chinese electronic semantic dictionaries. This sub-model is combined with modifier-head generation sub-model. After being optimized on the held out data by the EM algorithm, our improved parser achieves 79.4% (F1 measure), as well as a 4.4% relative decrease in error rate on the Penn Chinese Treebank (CTB). Further analysis of performance improvement indicates that semantic knowledge is helpful for nominal compounds, coordination, and NoV tagging disambiguation, as well as alleviating the sparseness of information available in treebank.
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000233302600007
出版者SPRINGER-VERLAG BERLIN
引用统计
被引频次:6[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://119.78.100.204/handle/2XEOYT63/9946
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Xiong, DY
作者单位1.Chinese Acad Sci, Comp Technol Inst, Beijing 100080, Peoples R China
2.Univ Sci & Technol Beijing, Beijing 100083, Peoples R China
3.Chinese Acad Sci, Grad Sch, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Xiong, DY,Li, SL,Liu, Q,et al. Parsing the Penn Chinese Treebank with semantic knowledge[J]. NATURAL LANGUAGE PROCESSING - IJCNLP 2005, PROCEEDINGS,2005,3651:70-81.
APA Xiong, DY,Li, SL,Liu, Q,Lin, SX,&Qian, YL.(2005).Parsing the Penn Chinese Treebank with semantic knowledge.NATURAL LANGUAGE PROCESSING - IJCNLP 2005, PROCEEDINGS,3651,70-81.
MLA Xiong, DY,et al."Parsing the Penn Chinese Treebank with semantic knowledge".NATURAL LANGUAGE PROCESSING - IJCNLP 2005, PROCEEDINGS 3651(2005):70-81.
条目包含的文件
条目无相关文件。
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
[Xiong, DY]的文章
[Li, SL]的文章
[Liu, Q]的文章
百度学术
百度学术中相似的文章
[Xiong, DY]的文章
[Li, SL]的文章
[Liu, Q]的文章
必应学术
必应学术中相似的文章
[Xiong, DY]的文章
[Li, SL]的文章
[Liu, Q]的文章
相关权益政策
暂无数据
收藏/分享
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。