For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Integration of Multiple Bilingually-Trained Segmentation Schemes into Statistical Machine Translation
Michael PAUL Andrew FINCH Eiichiro SUMITA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/03/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Natural Language Processing
statistical machine translation, word segmentation, machine learning, Asian languages,
Full Text: PDF>>
This paper proposes an unsupervised word segmentation algorithm that identifies word boundaries in continuous source language text in order to improve the translation quality of statistical machine translation (SMT) approaches. The method can be applied to any language pair in which the source language is unsegmented and the target language segmentation is known. In the first step, an iterative bootstrap method is applied to learn multiple segmentation schemes that are consistent with the phrasal segmentations of an SMT system trained on the resegmented bitext. In the second step, multiple segmentation schemes are integrated into a single SMT system by characterizing the source language side and merging identical translation pairs of differently segmented SMT models. Experimental results translating five Asian languages into English revealed that the proposed method of integrating multiple segmentation schemes outperforms SMT models trained on any of the learned word segmentations and performs comparably to available monolingually built segmentation tools.