Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents

Wei Yang; Zhongwen Zhao; Baosong Yang; Yves Lepage

Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents

Wei Yang, Zhongwen Zhao, Baosong Yang, Yves Lepage

Graduate School of Information, Production and Systems

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

1 Citation (Scopus)

Abstract

This paper describes Chinese-Japanese translation systems based on different alignment methods using the JPO corpus and our submission (ID: WASUIPS) to the subtask of the 2015 Workshop on Asian Translation. One of the alignment methods used is bilingual hierarchical sub-sentential alignment combined with sampling-based multilingual alignment. We also accelerated this method and in this paper, we evaluate the translation results and time spent on several machine translation tasks. The training time is much faster than the standard baseline pipeline (GIZA++/Moses) and MGIZA/Moses.

Original language	English
Pages	87-94
Number of pages	8
Publication status	Published - 2015
Event	2nd Workshop on Asian Translation, WAT 2015 - Kyoto, Japan Duration: 2015 Oct 16 → …

Conference

Conference	2nd Workshop on Asian Translation, WAT 2015
Country/Territory	Japan
City	Kyoto
Period	15/10/16 → …

ASJC Scopus subject areas

Language and Linguistics
Computer Science (miscellaneous)

Cite this

@conference{b5c4e750413e45f69e85cdfdbb08d499,

title = "Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents",

abstract = "This paper describes Chinese-Japanese translation systems based on different alignment methods using the JPO corpus and our submission (ID: WASUIPS) to the subtask of the 2015 Workshop on Asian Translation. One of the alignment methods used is bilingual hierarchical sub-sentential alignment combined with sampling-based multilingual alignment. We also accelerated this method and in this paper, we evaluate the translation results and time spent on several machine translation tasks. The training time is much faster than the standard baseline pipeline (GIZA++/Moses) and MGIZA/Moses.",

author = "Wei Yang and Zhongwen Zhao and Baosong Yang and Yves Lepage",

note = "Funding Information: The paper is part of the outcome of research performed under a Waseda University Grant for Special Research Project (Project number: 2015A-063). Publisher Copyright: {\textcopyright} 2015 Copyright is held by the author(s).; 2nd Workshop on Asian Translation, WAT 2015 ; Conference date: 16-10-2015",

year = "2015",

language = "English",

pages = "87--94",

}

TY - CONF

T1 - Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents

AU - Yang, Wei

AU - Zhao, Zhongwen

AU - Yang, Baosong

AU - Lepage, Yves

N1 - Funding Information: The paper is part of the outcome of research performed under a Waseda University Grant for Special Research Project (Project number: 2015A-063). Publisher Copyright: © 2015 Copyright is held by the author(s).

PY - 2015

Y1 - 2015

N2 - This paper describes Chinese-Japanese translation systems based on different alignment methods using the JPO corpus and our submission (ID: WASUIPS) to the subtask of the 2015 Workshop on Asian Translation. One of the alignment methods used is bilingual hierarchical sub-sentential alignment combined with sampling-based multilingual alignment. We also accelerated this method and in this paper, we evaluate the translation results and time spent on several machine translation tasks. The training time is much faster than the standard baseline pipeline (GIZA++/Moses) and MGIZA/Moses.

AB - This paper describes Chinese-Japanese translation systems based on different alignment methods using the JPO corpus and our submission (ID: WASUIPS) to the subtask of the 2015 Workshop on Asian Translation. One of the alignment methods used is bilingual hierarchical sub-sentential alignment combined with sampling-based multilingual alignment. We also accelerated this method and in this paper, we evaluate the translation results and time spent on several machine translation tasks. The training time is much faster than the standard baseline pipeline (GIZA++/Moses) and MGIZA/Moses.

UR - http://www.scopus.com/inward/record.url?scp=85123848450&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85123848450&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85123848450

SP - 87

EP - 94

T2 - 2nd Workshop on Asian Translation, WAT 2015

Y2 - 16 October 2015

ER -

Sampling-based Alignment and Hierarchical Sub-sentential Alignment in Chinese-Japanese Translation of Patents

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this