汉语框架语义角色的自动标注.doc

汉语框架语义角色的自动标注.docE・m ail: ******@ Tel/Fax: +86-10-62562563
ISSN 1000-9825. CODEN RUXUEW
Journal of Software. , , April 2010, -611 doi: .
© by Institute of Software, the Chinese Academy of Sciences. All rights reserved.
汉语框架语义角色的自动标注袞
李翘：王戢I,壬胃林1邦『
Y山西大学计算中心，山西太换030006)
Y山西大学数学科学学院，山西太原030006)
'(山西大学计算机与信息技术学院，山西太原030006)
Automatic Labeling of Semantic Roles on Chinese FrameNet
LIJi・Hong二 WANG Rui-Bo\ WANG Wei-Lin2, LI Guo-Chen3
1 (Computer Center. Shanxi University, Taiyuan 030006, China)
“School of Mathematical Sciences, Shanxi University, Taiyuan 030006, China)
\School of Computer and hformation Technology, Shanxi University, Taiyuan 030006, China)
+ Corresponding author: E-mail: ******@
Li JH, Wang RB, Wang WL, Li GC. Automatic labeling of semantic roles on Chinese FrameNet. Journal of Software^ 2010,21 (4):597-611. -9825/
Abstract: Based on the semantic knowledge base of Chinese FrameNet (CFN) self-developed by Shanxi University, automatic labeling of the semantic roles of Chinese FrameNet is turned into a sequential tagging problem at word-level by applying IOB (inside/outside/begin) strategies to the exemplified sentences in CFN corpus, and the Conditional Random Fields (CRF) model is adopted・ The basic unit of tagging is word・ The word, its part of speech, its relative position to the target word, the target word, and their combination are chosen as the features. Various model templates are formed through optional size windows in each feature, and the orthogonal array within statistics is employed for screening of the better template. All experiments are based on the6 692 exemplified sentences of 25 frames selected from CFN corpus・ The separate model is trained for each frame on its exemplified sentences by 2-fold cross-validation, and the processing of identification and classification for the semantic roles arc taken simultaneously. Finally, wi