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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Michael PAUL, Andrew FINCH, Eiichiro SUMITA, "Integration of Multiple Bilingually-Trained Segmentation Schemes into Statistical Machine Translation" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 3, pp. 690-697, March 2011, doi: 10.1587/transinf.E94.D.690.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.690/_p
Copy
@ARTICLE{e94-d_3_690,
author={Michael PAUL, Andrew FINCH, Eiichiro SUMITA, },
journal={IEICE TRANSACTIONS on Information},
title={Integration of Multiple Bilingually-Trained Segmentation Schemes into Statistical Machine Translation},
year={2011},
volume={E94-D},
number={3},
pages={690-697},
abstract={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.},
keywords={},
doi={10.1587/transinf.E94.D.690},
ISSN={1745-1361},
month={March},}
Copy
TY - JOUR
TI - Integration of Multiple Bilingually-Trained Segmentation Schemes into Statistical Machine Translation
T2 - IEICE TRANSACTIONS on Information
SP - 690
EP - 697
AU - Michael PAUL
AU - Andrew FINCH
AU - Eiichiro SUMITA
PY - 2011
DO - 10.1587/transinf.E94.D.690
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2011
AB - 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.
ER -