The NiCT-ATR Statistical Machine Translation System for the IWSLT 2006 Evaluation

Ruiqiang Zhang; Hirofumi Yamamoto; Michael Paul; Hideo Okuma; Keiji Yasuda; Yves Lepage; Etienne Denoual; Daichi Mochihashi; Andrew Finch; Eiichiro Sumita

The NiCT-ATR Statistical Machine Translation System for the IWSLT 2006 Evaluation

Ruiqiang Zhang, Hirofumi Yamamoto, Michael Paul, Hideo Okuma, Keiji Yasuda, Yves Lepage, Etienne Denoual, Daichi Mochihashi, Andrew Finch, Eiichiro Sumita

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

11 Citations (Scopus)

Abstract

This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and IE) and all two tracks (OPEN and CSTAR). We used a phrase-based SMT in the OPEN track and a hybrid multiple translation engine in the CSTAR track. We also equipped our system with some of new preprocessing and post-processing techniques for Chinese word segmentation, named entity translation, punctuation and capitalization, sentence splitting, and language model adaptation. Our experiments show these features significantly improved our system.

Original language	English
Pages	83-90
Number of pages	8
Publication status	Published - 2006
Externally published	Yes
Event	3rd International Workshop on Spoken Language Translation, IWSLT 2006 - Keihanna Science City, Japan Duration: 2006 Nov 27 → 2006 Nov 28

Conference

Conference	3rd International Workshop on Spoken Language Translation, IWSLT 2006
Country/Territory	Japan
City	Keihanna Science City
Period	06/11/27 → 06/11/28

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Linguistics and Language

Cite this

@conference{9fc8ebb6bc034303a59faa8ee9c63cda,

title = "The NiCT-ATR Statistical Machine Translation System for the IWSLT 2006 Evaluation",

abstract = "This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and IE) and all two tracks (OPEN and CSTAR). We used a phrase-based SMT in the OPEN track and a hybrid multiple translation engine in the CSTAR track. We also equipped our system with some of new preprocessing and post-processing techniques for Chinese word segmentation, named entity translation, punctuation and capitalization, sentence splitting, and language model adaptation. Our experiments show these features significantly improved our system.",

author = "Ruiqiang Zhang and Hirofumi Yamamoto and Michael Paul and Hideo Okuma and Keiji Yasuda and Yves Lepage and Etienne Denoual and Daichi Mochihashi and Andrew Finch and Eiichiro Sumita",

note = "Publisher Copyright: {\textcopyright} 2006 International Workshop on Spoken Language Translation, IWSLT 2006. All rights reserved.; 3rd International Workshop on Spoken Language Translation, IWSLT 2006 ; Conference date: 27-11-2006 Through 28-11-2006",

year = "2006",

language = "English",

pages = "83--90",

}

TY - CONF

T1 - The NiCT-ATR Statistical Machine Translation System for the IWSLT 2006 Evaluation

AU - Zhang, Ruiqiang

AU - Yamamoto, Hirofumi

AU - Paul, Michael

AU - Okuma, Hideo

AU - Yasuda, Keiji

AU - Lepage, Yves

AU - Denoual, Etienne

AU - Mochihashi, Daichi

AU - Finch, Andrew

AU - Sumita, Eiichiro

PY - 2006

Y1 - 2006

N2 - This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and IE) and all two tracks (OPEN and CSTAR). We used a phrase-based SMT in the OPEN track and a hybrid multiple translation engine in the CSTAR track. We also equipped our system with some of new preprocessing and post-processing techniques for Chinese word segmentation, named entity translation, punctuation and capitalization, sentence splitting, and language model adaptation. Our experiments show these features significantly improved our system.

AB - This paper describes the NiCT-ATR statistical machine translation (SMT) system used for the IWSLT 2006 evaluation compaign. We participated in all four language pair translation tasks (CE, JE, AE and IE) and all two tracks (OPEN and CSTAR). We used a phrase-based SMT in the OPEN track and a hybrid multiple translation engine in the CSTAR track. We also equipped our system with some of new preprocessing and post-processing techniques for Chinese word segmentation, named entity translation, punctuation and capitalization, sentence splitting, and language model adaptation. Our experiments show these features significantly improved our system.

UR - http://www.scopus.com/inward/record.url?scp=85133310104&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85133310104&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85133310104

SP - 83

EP - 90

T2 - 3rd International Workshop on Spoken Language Translation, IWSLT 2006

Y2 - 27 November 2006 through 28 November 2006

ER -

The NiCT-ATR Statistical Machine Translation System for the IWSLT 2006 Evaluation

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this