Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/3425
Title: Improving language modeling for (off-line) Chinese character recognition
Authors: Hung, Kei-yuen
Keywords: Hong Kong Polytechnic University -- Dissertations
Chinese language -- Data processing
Chinese character sets (Data processing)
Issue Date: 2002
Publisher: The Hong Kong Polytechnic University
Abstract: We analyze the error characteristics of a Chinese character recognizer and developed two approaches to improve Chinese character recognition system. We first develop a non-contiguous context dependent language model as a post processing module. The model makes use of far away context to predict the interested character. The model is only as good as the traditional bigram model in terms of accuracy. Secondly, we developed a method to detect errors in language model. The method employs pattern recognition technique. It combines both dictionary and statistical features to predict whether a block of character is correct or contains error. This detection scheme as demonstrated in our experiment is effective. The performance is 80%, 91% and 75% of precision, recall and skip ratio respectively.
Description: x, 79 leaves : ill. ; 30 cm.
PolyU Library Call No.: [THS] LG51 .H577M COMP 2002 Hung
URI: http://hdl.handle.net/10397/3425
Rights: All rights reserved.
Appears in Collections:Thesis

Files in This Item:
File Description SizeFormat 
b16259889_link.htmFor PolyU Users 162 BHTMLView/Open
b16259889_ir.pdfFor All Users (Non-printable) 2.8 MBAdobe PDFView/Open
Show full item record

Page view(s)

367
Last Week
4
Last month
Checked on Apr 30, 2017

Download(s)

184
Checked on Apr 30, 2017

Google ScholarTM

Check



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.