Chinese to Braille Translation Based on Braille Word Segmentation Using Statistical Model

Expand
  • (1. Beijing Key Laboratory of Mobile Computing and Pervasive Device, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; 2. Jiangsu Enterprise Information Operation Center, China Telecom Corporation Limited, Nanjing 210037, China; 3. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China)

Online published: 2017-04-04

Abstract

Automatic translation of Chinese text to Chinese Braille is important for blind people in China to acquire information using computers or smart phones. In this paper, a novel scheme of Chinese-Braille translation is proposed. Under the scheme, a Braille word segmentation model based on statistical machine learning is trained on a Braille corpus, and Braille word segmentation is carried out using the statistical model directly without the stage of Chinese word segmentation. This method avoids establishing rules concerning syntactic and semantic information and uses statistical model to learn the rules stealthily and automatically. To further improve the performance, an algorithm of fusing the results of Chinese word segmentation and Braille word segmentation is also proposed. Our results show that the proposed method achieves accuracy of 92.81% for Braille word segmentation and considerably outperforms current approaches using the segmentation-merging scheme.

Cite this article

WANG Xiangdong1,3* (王向东), YANG Yang2 (杨阳), ZHANG Jinchao3 (张金超), JIANG Wenbin3 (姜文斌), LIU Hong1,3 (刘 宏), QIAN Yueliang1,3 (钱跃良 . Chinese to Braille Translation Based on Braille Word Segmentation Using Statistical Model[J]. Journal of Shanghai Jiaotong University(Science), 2017 , 22(1) : 82 -086 . DOI: 10.1007/s12204-017-1804-x

References

[1] TENG W M, LI W H. Chinese Braille [M]. Beijing:China Press, 1996: 1-50 (in Chinese). [2] HUANG H Y, CHEN Z X, HUANG J. Chinese-Brailletranslation approach based on multi-knowledge analysis[C]//Language Computing and Content Based TextProcessing-Proceedings of the 7th Joint Symposiumon Computational Linguistics in China (JSCL-2003).Beijing: Tsinghua University Press, 2003: 607-613 (inChinese). [3] ZHU X Y, BAO T. EasyBraille: A translation systemfor Mandarin and Braille [C]//Natural Language Understandingand Machine Translation — Proceedingsof the 6th Joint Symposium on Computational Linguisticsin China (JSCL-2001). Beijing: Tsinghua UniversityPress, 2001: 326-331. [4] JIANG M H, ZHU X Y. Segmentation of MandarinBraille word and Braille translation based on multiknowledge[C]//Proceedings of International Conferenceon Signal Processing. Beijing: Publishing Houseof Electronics Industry, 2000: 2070-2074. [5] CHEN Y Y. Blind Chinese translation of wordsegmentationprocessing algorithm [J]. Network SecurityTechnology and Application, 2014, 2: 154-156 (inChinese). [6] LI H Q, FAN X Z, LI L F, et al. Research and implementationof Chinese-Braille machine translationsystem [J]. Journal of Computer Applications, 2002,22(11): 3-6 (in Chinese). [7] YANG C, CHE L. Design of Chinese-Braille conversionsystem [J]. Journal of Beijing Institute of GraphicCommunication, 2011, 19(6): 36-38 (in Chinese). [8] China National Standardizing Committee. ChineseBraille: GB/T 15720-2008 [S]. Beijing: StandardsPress of China, 2009: 5 (in Chinese).
Options
Outlines

/