Improving transliteration with precise alignment of phoneme chunks and using contextual features

Wei Gao, Kam Fai Wong, Wai Lam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Automatic transliteration of foreign names is basically regarded as a diminutive clone of the machine translation (MT) problem. It thus follows IBM's conventional MT models under the source-channel framework. Nonetheless, some parameters of this model dealing with zero-fertility words in the target sequences, can negatively impact transliteration effectiveness because of the inevitable inverted conditional probability estimation. Instead of source-channel, this paper presents a direct probabilistic transliteration model using contextual features of phonemes with a tailored alignment scheme for phoneme chunks. Experiments demonstrate superior performance over the source-channel for the task of English-Chinese transliteration.

Original languageEnglish
Title of host publicationLecture Notes in Computer Science
EditorsS.H. Myaeng, M. Zhou, H.J. Zhang, K.-F. Wong
Pages106-117
Number of pages12
Volume3411
Publication statusPublished - 2005
Externally publishedYes
EventAsia Information Retrieval Symposium, AIRS 2004 - Beijing, China
Duration: 18 Oct 200420 Oct 2004

Other

OtherAsia Information Retrieval Symposium, AIRS 2004
CountryChina
CityBeijing
Period18/10/0420/10/04

Fingerprint

Experiments
Statistical Models

ASJC Scopus subject areas

  • Computer Science (miscellaneous)

Cite this

Gao, W., Wong, K. F., & Lam, W. (2005). Improving transliteration with precise alignment of phoneme chunks and using contextual features. In S. H. Myaeng, M. Zhou, H. J. Zhang, & K-F. Wong (Eds.), Lecture Notes in Computer Science (Vol. 3411, pp. 106-117)

Improving transliteration with precise alignment of phoneme chunks and using contextual features. / Gao, Wei; Wong, Kam Fai; Lam, Wai.

Lecture Notes in Computer Science. ed. / S.H. Myaeng; M. Zhou; H.J. Zhang; K.-F. Wong. Vol. 3411 2005. p. 106-117.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gao, W, Wong, KF & Lam, W 2005, Improving transliteration with precise alignment of phoneme chunks and using contextual features. in SH Myaeng, M Zhou, HJ Zhang & K-F Wong (eds), Lecture Notes in Computer Science. vol. 3411, pp. 106-117, Asia Information Retrieval Symposium, AIRS 2004, Beijing, China, 18/10/04.
Gao W, Wong KF, Lam W. Improving transliteration with precise alignment of phoneme chunks and using contextual features. In Myaeng SH, Zhou M, Zhang HJ, Wong K-F, editors, Lecture Notes in Computer Science. Vol. 3411. 2005. p. 106-117
Gao, Wei ; Wong, Kam Fai ; Lam, Wai. / Improving transliteration with precise alignment of phoneme chunks and using contextual features. Lecture Notes in Computer Science. editor / S.H. Myaeng ; M. Zhou ; H.J. Zhang ; K.-F. Wong. Vol. 3411 2005. pp. 106-117
@inproceedings{310e9affca844fbdb4261381faca3d06,
title = "Improving transliteration with precise alignment of phoneme chunks and using contextual features",
abstract = "Automatic transliteration of foreign names is basically regarded as a diminutive clone of the machine translation (MT) problem. It thus follows IBM's conventional MT models under the source-channel framework. Nonetheless, some parameters of this model dealing with zero-fertility words in the target sequences, can negatively impact transliteration effectiveness because of the inevitable inverted conditional probability estimation. Instead of source-channel, this paper presents a direct probabilistic transliteration model using contextual features of phonemes with a tailored alignment scheme for phoneme chunks. Experiments demonstrate superior performance over the source-channel for the task of English-Chinese transliteration.",
author = "Wei Gao and Wong, {Kam Fai} and Wai Lam",
year = "2005",
language = "English",
volume = "3411",
pages = "106--117",
editor = "S.H. Myaeng and M. Zhou and H.J. Zhang and K.-F. Wong",
booktitle = "Lecture Notes in Computer Science",

}

TY - GEN

T1 - Improving transliteration with precise alignment of phoneme chunks and using contextual features

AU - Gao, Wei

AU - Wong, Kam Fai

AU - Lam, Wai

PY - 2005

Y1 - 2005

N2 - Automatic transliteration of foreign names is basically regarded as a diminutive clone of the machine translation (MT) problem. It thus follows IBM's conventional MT models under the source-channel framework. Nonetheless, some parameters of this model dealing with zero-fertility words in the target sequences, can negatively impact transliteration effectiveness because of the inevitable inverted conditional probability estimation. Instead of source-channel, this paper presents a direct probabilistic transliteration model using contextual features of phonemes with a tailored alignment scheme for phoneme chunks. Experiments demonstrate superior performance over the source-channel for the task of English-Chinese transliteration.

AB - Automatic transliteration of foreign names is basically regarded as a diminutive clone of the machine translation (MT) problem. It thus follows IBM's conventional MT models under the source-channel framework. Nonetheless, some parameters of this model dealing with zero-fertility words in the target sequences, can negatively impact transliteration effectiveness because of the inevitable inverted conditional probability estimation. Instead of source-channel, this paper presents a direct probabilistic transliteration model using contextual features of phonemes with a tailored alignment scheme for phoneme chunks. Experiments demonstrate superior performance over the source-channel for the task of English-Chinese transliteration.

UR - http://www.scopus.com/inward/record.url?scp=24344445266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24344445266&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:24344445266

VL - 3411

SP - 106

EP - 117

BT - Lecture Notes in Computer Science

A2 - Myaeng, S.H.

A2 - Zhou, M.

A2 - Zhang, H.J.

A2 - Wong, K.-F.

ER -