Presentation 1997/7/25
Extracting Kana-alphabet rules from a non-Japanese name reading table
Keiko Masuda, Kyoji Umemura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have a dictionary that converts alphabet of person names into their corresponding Kana. The correspondence rules between alphabet and Kana are valuable when Japanese people search foreign names. We have tried to extract these rules from the dictionary. In this paper, we propose the algorithm that can extract the rules. Then we have applied the algorithm to the actual data. Finally, we have verified the correctness of the rules against original dictionary. It is remarkable that this algorithm is able to extract rules without any given information of Kana-alphabet correspondence.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) morphology / corpus / statistical processing
Paper # NLC97-22
Date of Issue

Conference Information
Committee NLC
Conference Date 1997/7/25(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 Kana-alphabet rules from a non-Japanese name reading table
Sub Title (in English)
Keyword(1) morphology
Keyword(2) corpus
Keyword(3) statistical processing
1st Author's Name Keiko Masuda
1st Author's Affiliation Umemura Laboratory, Department of Information and Computer Sciences()
2nd Author's Name Kyoji Umemura
2nd Author's Affiliation Umemura Laboratory, Department of Information and Computer Sciences
Date 1997/7/25
Paper # NLC97-22
Volume (vol) vol.97
Number (no) 200
Page pp.pp.-
#Pages 6
Date of Issue