Presentation 1998/5/15
Automatic Generation of Dependency Rules for Japanese Noun Phrases with Particles"no"
Shinji NAKAI, Satoru IKEHARA, Satoshi SHIRAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposed a method automatically to generate dependency rules for "A no B no C", the most typical noun phrases and frequently appeared in Japanese (similar to "C of B of A" in English), using a semantic attribute system currently developed. In this method, 3 kinds of semantic dependency rules such as one-, two-, tree-dimensional rules are independently generated from a noun phrase data-base. In the experiments, the generated rules were applied to the dependency analysis (in the order of 1-, 2- and 3-dimensional rules) resulting in the recall rate of 96.0%, precision rate of 88.4%, accuracy rate of 85.1%.From these result, it was found that the method yields accurate rules for dependency analysis.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Noun Analysis / Dependency Rule / Machine Learning / Generalization
Paper #
Date of Issue

Conference Information
Committee NLC
Conference Date 1998/5/15(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) Automatic Generation of Dependency Rules for Japanese Noun Phrases with Particles"no"
Sub Title (in English)
Keyword(1) Noun Analysis
Keyword(2) Dependency Rule
Keyword(3) Machine Learning
Keyword(4) Generalization
1st Author's Name Shinji NAKAI
1st Author's Affiliation Faculty of Engineering, Tottori University()
2nd Author's Name Satoru IKEHARA
2nd Author's Affiliation Faculty of Engineering, Tottori University
3rd Author's Name Satoshi SHIRAI
3rd Author's Affiliation NTT Communication Science Laboratories
Date 1998/5/15
Paper #
Volume (vol) vol.98
Number (no) 53
Page pp.pp.-
#Pages 8
Date of Issue