DocumentCode
2751194
Title
Resolution to Combinational Ambiguity of Chinese Word Segmentation
Author
Liu, JiangYang ; Liu, Ying
Author_Institution
Dept. of Chinese Language & Literature, Tsinghua Univ., Beijing, China
fYear
2009
fDate
5-6 Dec. 2009
Firstpage
141
Lastpage
145
Abstract
Chinese word segmentation ambiguity can be divided into two categories: overlapped ambiguity and combinational ambiguity. This paper only focuses on the resolution to combinational ambiguity of Chinese word segmentation. We select 36 typical combinational ambiguity strings, and make use of transformation-based learning methods to learn the rules of combinational ambiguity. Using these rules to test "People\´s Daily" Corpus of 1996, we find that the average precision rate is improved from 79.08% to 94.35%.
Keywords
learning (artificial intelligence); word processing; Chinese word segmentation; combinational ambiguity; overlapped ambiguity; transformation-based learning methods; Electronic government; Electronic learning; Error analysis; Error correction; Information systems; Learning systems; Natural languages; Tagging; Testing; White spaces; combinational ambiguity; disambiguation; transformation-based learning;
fLanguage
English
Publisher
ieee
Conference_Titel
E-Learning, E-Business, Enterprise Information Systems, and E-Government, 2009. EEEE '09. International Conference on
Conference_Location
Hong Kong
Print_ISBN
978-0-7695-3907-2
Type
conf
DOI
10.1109/EEEE.2009.38
Filename
5359162
Link To Document