Braille translation based on multi-knowledge

M. H. Jiang, X. Y. Zun, Y. Xia, Gang Tan, T. Bao

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The transformation from Braille to Mandarin Characters can be divided into two steps: from Braille to Pinyin and from Pinyin to Mandarin Characters. Incorporating the Legal Pinyin Table into our system the ambiguity problem was solved in the transformation from Braille to Pinyin. A standard statistical Bigram Markov model was used in the subsystem to transform Pinyin to Mandarin Characters. Then two modifications of the smoothing method which are consistent with the phrase-level Bigram model were proposed to overcome the sparse data problem in our system model. For each Pinyin sentence, a multi-level graph was used with the Viterbi algorithm to search for the best Mandarin sentence in the maximal likelihood. The measurement of N-best algorithm was studied to get N best Mandarin sentences. Experiments show that the correct rate of the system is 94. 38%. If proper nouns are not considered, our system can achieve a further 2% improvement. The accuracy rate for the top-5 hypothesis by using N-Best algorithm is 3% higher than that of the best hypothesis.

Original languageEnglish (US)
Pages (from-to)69-73
Number of pages5
JournalQinghua Daxue Xuebao/Journal of Tsinghua University
Volume40
Issue number9
StatePublished - Sep 1 2000

Fingerprint

Viterbi algorithm
Viterbi Algorithm
Sparse Data
Smoothing Methods
Markov Model
Statistical Model
Likelihood
Table
Subsystem
Transform
Knowledge
Graph in graph theory
Experiments
Model
Experiment
Character
Standards
Ambiguity

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Applied Mathematics

Cite this

Jiang, M. H., Zun, X. Y., Xia, Y., Tan, G., & Bao, T. (2000). Braille translation based on multi-knowledge. Qinghua Daxue Xuebao/Journal of Tsinghua University, 40(9), 69-73.
Jiang, M. H. ; Zun, X. Y. ; Xia, Y. ; Tan, Gang ; Bao, T. / Braille translation based on multi-knowledge. In: Qinghua Daxue Xuebao/Journal of Tsinghua University. 2000 ; Vol. 40, No. 9. pp. 69-73.
@article{652224da5c9840f5b6f88916d850a404,
title = "Braille translation based on multi-knowledge",
abstract = "The transformation from Braille to Mandarin Characters can be divided into two steps: from Braille to Pinyin and from Pinyin to Mandarin Characters. Incorporating the Legal Pinyin Table into our system the ambiguity problem was solved in the transformation from Braille to Pinyin. A standard statistical Bigram Markov model was used in the subsystem to transform Pinyin to Mandarin Characters. Then two modifications of the smoothing method which are consistent with the phrase-level Bigram model were proposed to overcome the sparse data problem in our system model. For each Pinyin sentence, a multi-level graph was used with the Viterbi algorithm to search for the best Mandarin sentence in the maximal likelihood. The measurement of N-best algorithm was studied to get N best Mandarin sentences. Experiments show that the correct rate of the system is 94. 38{\%}. If proper nouns are not considered, our system can achieve a further 2{\%} improvement. The accuracy rate for the top-5 hypothesis by using N-Best algorithm is 3{\%} higher than that of the best hypothesis.",
author = "Jiang, {M. H.} and Zun, {X. Y.} and Y. Xia and Gang Tan and T. Bao",
year = "2000",
month = "9",
day = "1",
language = "English (US)",
volume = "40",
pages = "69--73",
journal = "Qinghua Daxue Xuebao/Journal of Tsinghua University",
issn = "1000-0054",
publisher = "Press of Tsinghua University",
number = "9",

}

Jiang, MH, Zun, XY, Xia, Y, Tan, G & Bao, T 2000, 'Braille translation based on multi-knowledge', Qinghua Daxue Xuebao/Journal of Tsinghua University, vol. 40, no. 9, pp. 69-73.

Braille translation based on multi-knowledge. / Jiang, M. H.; Zun, X. Y.; Xia, Y.; Tan, Gang; Bao, T.

In: Qinghua Daxue Xuebao/Journal of Tsinghua University, Vol. 40, No. 9, 01.09.2000, p. 69-73.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Braille translation based on multi-knowledge

AU - Jiang, M. H.

AU - Zun, X. Y.

AU - Xia, Y.

AU - Tan, Gang

AU - Bao, T.

PY - 2000/9/1

Y1 - 2000/9/1

N2 - The transformation from Braille to Mandarin Characters can be divided into two steps: from Braille to Pinyin and from Pinyin to Mandarin Characters. Incorporating the Legal Pinyin Table into our system the ambiguity problem was solved in the transformation from Braille to Pinyin. A standard statistical Bigram Markov model was used in the subsystem to transform Pinyin to Mandarin Characters. Then two modifications of the smoothing method which are consistent with the phrase-level Bigram model were proposed to overcome the sparse data problem in our system model. For each Pinyin sentence, a multi-level graph was used with the Viterbi algorithm to search for the best Mandarin sentence in the maximal likelihood. The measurement of N-best algorithm was studied to get N best Mandarin sentences. Experiments show that the correct rate of the system is 94. 38%. If proper nouns are not considered, our system can achieve a further 2% improvement. The accuracy rate for the top-5 hypothesis by using N-Best algorithm is 3% higher than that of the best hypothesis.

AB - The transformation from Braille to Mandarin Characters can be divided into two steps: from Braille to Pinyin and from Pinyin to Mandarin Characters. Incorporating the Legal Pinyin Table into our system the ambiguity problem was solved in the transformation from Braille to Pinyin. A standard statistical Bigram Markov model was used in the subsystem to transform Pinyin to Mandarin Characters. Then two modifications of the smoothing method which are consistent with the phrase-level Bigram model were proposed to overcome the sparse data problem in our system model. For each Pinyin sentence, a multi-level graph was used with the Viterbi algorithm to search for the best Mandarin sentence in the maximal likelihood. The measurement of N-best algorithm was studied to get N best Mandarin sentences. Experiments show that the correct rate of the system is 94. 38%. If proper nouns are not considered, our system can achieve a further 2% improvement. The accuracy rate for the top-5 hypothesis by using N-Best algorithm is 3% higher than that of the best hypothesis.

UR - http://www.scopus.com/inward/record.url?scp=0034260166&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034260166&partnerID=8YFLogxK

M3 - Article

VL - 40

SP - 69

EP - 73

JO - Qinghua Daxue Xuebao/Journal of Tsinghua University

JF - Qinghua Daxue Xuebao/Journal of Tsinghua University

SN - 1000-0054

IS - 9

ER -