Presentation 1996/10/11
Learning Subcategorization Preferences with a Hidden Variable : Coping with Case Dependencies and Noun Class Generalization
Takehito UTSURO, Yuji MATSUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a novel method for learning probabilistic parameters for calculating subcategorization preference functions. In the method, for the purpose of coping with ambiguities of dependencies and noun class generalization of argument/ajunct nouns, we introduce a hidden variable which takes a tupple of independent partial subcategorization frames as its value. Each collocation of a verb and argument/adjunct nouns is assumed to be generated from one of the possible values of the hidden variable. Probabilistic parameters are then estimated so as to maximize the subcategorization preference function for each collocation of a verb and argument/adjunct nouns in the training corpus. We also describe the experimental results of learning probabilistic parameters from the EDR Japanese bracketed corpus.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) corpus / subcategorization / hidden variable / collocation / preference / case frame
Paper # NLC96-35
Date of Issue

Conference Information
Committee NLC
Conference Date 1996/10/11(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) Learning Subcategorization Preferences with a Hidden Variable : Coping with Case Dependencies and Noun Class Generalization
Sub Title (in English)
Keyword(1) corpus
Keyword(2) subcategorization
Keyword(3) hidden variable
Keyword(4) collocation
Keyword(5) preference
Keyword(6) case frame
1st Author's Name Takehito UTSURO
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Yuji MATSUMOTO
2nd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 1996/10/11
Paper # NLC96-35
Volume (vol) vol.96
Number (no) 294
Page pp.pp.-
#Pages 8
Date of Issue