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

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)