Presentation 2002/7/22
Machine Learning Based Analysis of Japanese Braille Transcription : toward the Development of Transcription System for Japanese Braille Translation
Aki SUGANO, Yutaka TAKAOKA, Ryuichi YONEDA, Kentaro INUI, Yuji MATSUMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper investigates various types of Japanese Braille transcription and proposes an analysis of chunk boundaries based on Support Vector Machine. This learning model can acquire chunk boundaries in Japanese Braille without describing rules. The paper discusses ambiguities in Japanese Braille transcription rules and the difficulty of translating Japanese into Japanese Braille. A preliminary experiment suggests that the learning model can achieve high precision in learning chunk boundaries of Japanese Braille text including exceptional transcriptions.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Japanese Braille transcription rules / chunk boundaries / Machine Learning
Paper # TL2002-11
Date of Issue

Conference Information
Committee TL
Conference Date 2002/7/22(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 Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Machine Learning Based Analysis of Japanese Braille Transcription : toward the Development of Transcription System for Japanese Braille Translation
Sub Title (in English)
Keyword(1) Japanese Braille transcription rules
Keyword(2) chunk boundaries
Keyword(3) Machine Learning
1st Author's Name Aki SUGANO
1st Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology()
2nd Author's Name Yutaka TAKAOKA
2nd Author's Affiliation Iwate Medical University School of Dentistry
3rd Author's Name Ryuichi YONEDA
3rd Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
4th Author's Name Kentaro INUI
4th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
5th Author's Name Yuji MATSUMOTO
5th Author's Affiliation Graduate School of Information Science, Nara Institute of Science and Technology
Date 2002/7/22
Paper # TL2002-11
Volume (vol) vol.102
Number (no) 254
Page pp.pp.-
#Pages 6
Date of Issue