Preordering for Chinese-Vietnamese Statistical Machine Translation

Huu-Anh TRAN; Heyan HUANG; Phuoc TRAN; Shumin SHI; Huu NGUYEN

doi:10.1587/transinf.2018EDP7211

Preordering for Chinese-Vietnamese Statistical Machine Translation

Huu-Anh TRAN, Heyan HUANG, Phuoc TRAN, Shumin SHI, Huu NGUYEN

Full Text Views

0

Cite this

Summary :

Word order is one of the most significant differences between the Chinese and Vietnamese. In the phrase-based statistical machine translation, the reordering model will learn reordering rules from bilingual corpora. If the bilingual corpora are large and good enough, the reordering rules are exact and coverable. However, Chinese-Vietnamese is a low-resource language pair, the extraction of reordering rules is limited. This leads to the quality of reordering in Chinese-Vietnamese machine translation is not high. In this paper, we have combined Chinese dependency relation and Chinese-Vietnamese word alignment results in order to pre-order Chinese word order to be suitable to Vietnamese one. The experimental results show that our methodology has improved the machine translation performance compared to the translation system using only the reordering models of phrase-based statistical machine translation.

Publication: IEICE TRANSACTIONS on Information Vol.E102-D No.2 pp.375-382

Publication Date: 2019/02/01

Publicized: 2018/11/12

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2018EDP7211

Type of Manuscript: PAPER

Category: Natural Language Processing

Authors

Huu-Anh TRAN
  Beijing Institute of Technology
Heyan HUANG
  Beijing Institute of Technology
Phuoc TRAN
  Ton Duc Thang University
Shumin SHI
  Beijing Institute of Technology
Huu NGUYEN
  Ho Chi Minh City University of Food Industry

Keyword

Chinese-Vietnamese machine translation, preordering, word alignment, Chinese grammatical relations, dependency relations

Cite this

Copy

Huu-Anh TRAN, Heyan HUANG, Phuoc TRAN, Shumin SHI, Huu NGUYEN, "Preordering for Chinese-Vietnamese Statistical Machine Translation" in IEICE TRANSACTIONS on Information, vol. E102-D, no. 2, pp. 375-382, February 2019, doi: 10.1587/transinf.2018EDP7211.
Abstract: Word order is one of the most significant differences between the Chinese and Vietnamese. In the phrase-based statistical machine translation, the reordering model will learn reordering rules from bilingual corpora. If the bilingual corpora are large and good enough, the reordering rules are exact and coverable. However, Chinese-Vietnamese is a low-resource language pair, the extraction of reordering rules is limited. This leads to the quality of reordering in Chinese-Vietnamese machine translation is not high. In this paper, we have combined Chinese dependency relation and Chinese-Vietnamese word alignment results in order to pre-order Chinese word order to be suitable to Vietnamese one. The experimental results show that our methodology has improved the machine translation performance compared to the translation system using only the reordering models of phrase-based statistical machine translation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7211/_p

Copy

@ARTICLE{e102-d_2_375,
author={Huu-Anh TRAN, Heyan HUANG, Phuoc TRAN, Shumin SHI, Huu NGUYEN, },
journal={IEICE TRANSACTIONS on Information},
title={Preordering for Chinese-Vietnamese Statistical Machine Translation},
year={2019},
volume={E102-D},
number={2},
pages={375-382},
abstract={Word order is one of the most significant differences between the Chinese and Vietnamese. In the phrase-based statistical machine translation, the reordering model will learn reordering rules from bilingual corpora. If the bilingual corpora are large and good enough, the reordering rules are exact and coverable. However, Chinese-Vietnamese is a low-resource language pair, the extraction of reordering rules is limited. This leads to the quality of reordering in Chinese-Vietnamese machine translation is not high. In this paper, we have combined Chinese dependency relation and Chinese-Vietnamese word alignment results in order to pre-order Chinese word order to be suitable to Vietnamese one. The experimental results show that our methodology has improved the machine translation performance compared to the translation system using only the reordering models of phrase-based statistical machine translation.},
keywords={},
doi={10.1587/transinf.2018EDP7211},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Preordering for Chinese-Vietnamese Statistical Machine Translation
T2 - IEICE TRANSACTIONS on Information
SP - 375
EP - 382
AU - Huu-Anh TRAN
AU - Heyan HUANG
AU - Phuoc TRAN
AU - Shumin SHI
AU - Huu NGUYEN
PY - 2019
DO - 10.1587/transinf.2018EDP7211
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2019
AB - Word order is one of the most significant differences between the Chinese and Vietnamese. In the phrase-based statistical machine translation, the reordering model will learn reordering rules from bilingual corpora. If the bilingual corpora are large and good enough, the reordering rules are exact and coverable. However, Chinese-Vietnamese is a low-resource language pair, the extraction of reordering rules is limited. This leads to the quality of reordering in Chinese-Vietnamese machine translation is not high. In this paper, we have combined Chinese dependency relation and Chinese-Vietnamese word alignment results in order to pre-order Chinese word order to be suitable to Vietnamese one. The experimental results show that our methodology has improved the machine translation performance compared to the translation system using only the reordering models of phrase-based statistical machine translation.
ER -