Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation

Maxim Khalilov; Jose Fonollosa; Mark Dras

Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation

Maxim Khalilov, Jose Fonollosa, Mark Dras

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

3 Citations (Scopus)

Abstract

In this paper, we start with the existing idea of taking reordering rules automatically derived from syntactic representations, and applying them in a preprocessing step before translation to make the source sentence structurally more like the target; and we propose a new approach to hierarchically extracting these rules. We evaluate this, combined with a lattice-based decoding, and show improvements over state-of-the-art distortion models.

Original language	English
Title of host publication	Proceedings of SSST-3
Subtitle of host publication	third Workshop on Syntax and Structure in Statistical Translation
Editors	Dekai Wu, David Chiang
Place of Publication	Stroudsburg, PA, USA
Publisher	Association for Computational Linguistics
Pages	78-86
Number of pages	9
ISBN (Print)	9781932432398
Publication status	Published - 2009
Event	Third Workshop on Syntax and Structure in Statistical Translation (SSST-3) - Boulder, Colorado Duration: 5 Jun 2009 → 5 Jun 2009

Workshop

Workshop	Third Workshop on Syntax and Structure in Statistical Translation (SSST-3)
City	Boulder, Colorado
Period	5/06/09 → 5/06/09

Access to Document

http://www.mt-archive.info/SSST-2009-TOC.htm

Cite this

@inproceedings{8afa9f98aa1c40858a86ce2265578f3b,

title = "Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation",

abstract = "In this paper, we start with the existing idea of taking reordering rules automatically derived from syntactic representations, and applying them in a preprocessing step before translation to make the source sentence structurally more like the target; and we propose a new approach to hierarchically extracting these rules. We evaluate this, combined with a lattice-based decoding, and show improvements over state-of-the-art distortion models.",

author = "Maxim Khalilov and Jose Fonollosa and Mark Dras",

year = "2009",

language = "English",

isbn = "9781932432398",

pages = "78--86",

editor = "Dekai Wu and David Chiang",

booktitle = "Proceedings of SSST-3",

publisher = "Association for Computational Linguistics",

note = "Third Workshop on Syntax and Structure in Statistical Translation (SSST-3) ; Conference date: 05-06-2009 Through 05-06-2009",

}

Khalilov, M, Fonollosa, J & Dras, M 2009, Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation. in D Wu & D Chiang (eds), Proceedings of SSST-3: third Workshop on Syntax and Structure in Statistical Translation. Association for Computational Linguistics, Stroudsburg, PA, USA, pp. 78-86, Third Workshop on Syntax and Structure in Statistical Translation (SSST-3), Boulder, Colorado, 5/06/09. <http://www.mt-archive.info/SSST-2009-TOC.htm>

Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation. / Khalilov, Maxim; Fonollosa, Jose; Dras, Mark.
Proceedings of SSST-3: third Workshop on Syntax and Structure in Statistical Translation. ed. / Dekai Wu; David Chiang. Stroudsburg, PA, USA: Association for Computational Linguistics, 2009. p. 78-86.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation

AU - Khalilov, Maxim

AU - Fonollosa, Jose

AU - Dras, Mark

PY - 2009

Y1 - 2009

N2 - In this paper, we start with the existing idea of taking reordering rules automatically derived from syntactic representations, and applying them in a preprocessing step before translation to make the source sentence structurally more like the target; and we propose a new approach to hierarchically extracting these rules. We evaluate this, combined with a lattice-based decoding, and show improvements over state-of-the-art distortion models.

AB - In this paper, we start with the existing idea of taking reordering rules automatically derived from syntactic representations, and applying them in a preprocessing step before translation to make the source sentence structurally more like the target; and we propose a new approach to hierarchically extracting these rules. We evaluate this, combined with a lattice-based decoding, and show improvements over state-of-the-art distortion models.

M3 - Conference proceeding contribution

SN - 9781932432398

SP - 78

EP - 86

BT - Proceedings of SSST-3

A2 - Wu, Dekai

A2 - Chiang, David

PB - Association for Computational Linguistics

CY - Stroudsburg, PA, USA

T2 - Third Workshop on Syntax and Structure in Statistical Translation (SSST-3)

Y2 - 5 June 2009 through 5 June 2009

ER -

Coupling hierarchical word reordering and decoding in phrase-based statistical machine translation

Abstract

Workshop

Access to Document

Fingerprint

Cite this