Head-modifier relation based non-lexical reordering model for phrase-based translation

Shui Liu; Sheng Li; Tiejun Zhao; Min Zhang; Pengyuan Liu

Head-modifier relation based non-lexical reordering model for phrase-based translation

Shui Liu^*
, Sheng Li
, Tiejun Zhao
, Min Zhang
, Pengyuan Liu

^*Corresponding author for this work

Faculty of Computing

Harbin Institute of Technology
Agency for Science, Technology and Research, Singapore
Peking University

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

Phrase-based statistical MT (SMT) is a milestone in MT. However, the translation model in the phrase based SMT is structure free which greatly limits its reordering capacity. To address this issue, we propose a non-lexical headmodifier based reordering model on word level by utilizing constituent based parse tree in source side. Our experimental results on the NIST Chinese- English benchmarking data show that, with a very small size model, our method significantly outperforms the baseline by 1.48% bleu score.

Original language	English
Pages	748-756
Number of pages	9
State	Published - 2010
Event	23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China Duration: 23 Aug 2010 → 27 Aug 2010

Conference

Conference	23rd International Conference on Computational Linguistics, Coling 2010
Country/Territory	China
City	Beijing
Period	23/08/10 → 27/08/10

Cite this

@conference{773a966b83ab4b4ea91a7449c948ce5a,

title = "Head-modifier relation based non-lexical reordering model for phrase-based translation",

abstract = "Phrase-based statistical MT (SMT) is a milestone in MT. However, the translation model in the phrase based SMT is structure free which greatly limits its reordering capacity. To address this issue, we propose a non-lexical headmodifier based reordering model on word level by utilizing constituent based parse tree in source side. Our experimental results on the NIST Chinese- English benchmarking data show that, with a very small size model, our method significantly outperforms the baseline by 1.48\% bleu score.",

author = "Shui Liu and Sheng Li and Tiejun Zhao and Min Zhang and Pengyuan Liu",

year = "2010",

language = "英语",

pages = "748--756",

note = "23rd International Conference on Computational Linguistics, Coling 2010 ; Conference date: 23-08-2010 Through 27-08-2010",

}

TY - CONF

T1 - Head-modifier relation based non-lexical reordering model for phrase-based translation

AU - Liu, Shui

AU - Li, Sheng

AU - Zhao, Tiejun

AU - Zhang, Min

AU - Liu, Pengyuan

PY - 2010

Y1 - 2010

N2 - Phrase-based statistical MT (SMT) is a milestone in MT. However, the translation model in the phrase based SMT is structure free which greatly limits its reordering capacity. To address this issue, we propose a non-lexical headmodifier based reordering model on word level by utilizing constituent based parse tree in source side. Our experimental results on the NIST Chinese- English benchmarking data show that, with a very small size model, our method significantly outperforms the baseline by 1.48% bleu score.

AB - Phrase-based statistical MT (SMT) is a milestone in MT. However, the translation model in the phrase based SMT is structure free which greatly limits its reordering capacity. To address this issue, we propose a non-lexical headmodifier based reordering model on word level by utilizing constituent based parse tree in source side. Our experimental results on the NIST Chinese- English benchmarking data show that, with a very small size model, our method significantly outperforms the baseline by 1.48% bleu score.

UR - https://www.scopus.com/pages/publications/80053402889

M3 - 论文

AN - SCOPUS:80053402889

SP - 748

EP - 756

T2 - 23rd International Conference on Computational Linguistics, Coling 2010

Y2 - 23 August 2010 through 27 August 2010

ER -

Head-modifier relation based non-lexical reordering model for phrase-based translation

Abstract

Conference

Other files and links

Fingerprint

Cite this