Presentation 2000/3/17
A method to detect and correct erroneous characters wrongly inserted, substituted and deleted in Japanese sentence using Skipped Markov chain models
Tetsuo ARAKI, Satoru IKEHARA, Norihisa HASHIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In optical character recognition and continuous speech recognition of a natural language, there are erroneous characters that have been wrongly substituted, inserted and deleted. We have previously proposed a method to detect and correct these errors using the Markov chain model. In this paper, we propose a improved method to detect erroneous characters wrongly deleted, and compound errors of wrongly inserted, substituted and deleted characters, using skipped Markov chain models. From the results of the experiments, it is concluded that this method is useful for detecting as well as correcting these erroneous characters.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Markov chain model / Skipped Markov chain models / wrongly deleted characters / Compound error strings
Paper # NLC99-78,PRMU99-261
Date of Issue

Conference Information
Committee NLC
Conference Date 2000/3/17(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) A method to detect and correct erroneous characters wrongly inserted, substituted and deleted in Japanese sentence using Skipped Markov chain models
Sub Title (in English)
Keyword(1) Markov chain model
Keyword(2) Skipped Markov chain models
Keyword(3) wrongly deleted characters
Keyword(4) Compound error strings
1st Author's Name Tetsuo ARAKI
1st Author's Affiliation Department of Human and artificial Intelligent Systems, Factory of Engineering, Fukui Univ.()
2nd Author's Name Satoru IKEHARA
2nd Author's Affiliation Department of Intelligence Information Engineering, Faculty of Engineering, Tottori Univ.
3rd Author's Name Norihisa HASHIMOTO
3rd Author's Affiliation Department of Human and artificial Intelligent Systems, Factory of Engineering, Fukui Univ.
Date 2000/3/17
Paper # NLC99-78,PRMU99-261
Volume (vol) vol.99
Number (no) 708
Page pp.pp.-
#Pages 8
Date of Issue