Presentation 1998/7/23
Extracting Preference of Dependency between Japanese Subordinate Clauses from Corpus
Shigeyuki Nishiokayama, Takehito Utsuro, Yuji Matsumoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Dependeny analysisi of Japanese subordinate clauses is one of the most difficult phase in the syntactic analysis of Japanese long setences. This paper proposes a corpus-based method of learning preference rule of deciding dependency relation of Japanese subordinate clauses. We utilize morphological cues included in the subordinate clauses and statistically estimate the co-relation of those cues and dependency relation of Japanese subordinate clauses. In the experimental evalution on EDR Japanese parsed corpus, we discover that there exist several morphological cues that are quite effective in deciding dependency relation of Japanese subordinate clauses.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) statistical language processing / Japanese subordinate clause / dependency analysis / corpus / decision list / preference
Paper # NLC98-11
Date of Issue

Conference Information
Committee NLC
Conference Date 1998/7/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Natural Language Understanding and Models of Communication (NLC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Extracting Preference of Dependency between Japanese Subordinate Clauses from Corpus
Sub Title (in English)
Keyword(1) statistical language processing
Keyword(2) Japanese subordinate clause
Keyword(3) dependency analysis
Keyword(4) corpus
Keyword(5) decision list
Keyword(6) preference
1st Author's Name Shigeyuki Nishiokayama
1st Author's Affiliation Graduate School of Language and Culture, Osaka University()
2nd Author's Name Takehito Utsuro
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
3rd Author's Name Yuji Matsumoto
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 1998/7/23
Paper # NLC98-11
Volume (vol) vol.98
Number (no) 209
Page pp.pp.-
#Pages 8
Date of Issue