The operation sequencemodel—combining N-gram-based and phrase-based statistical machine translation

Nadir Durrani, Helmut Schmid, Alexander Fraser, Philipp Koehn, Hinrich Schütze

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on minimal translation units, (ii) takes both source and target information into account, (iii) does not make a phrasal independence assumption, and (iv) avoids the spurious phrasal segmentation problem. As in phrase-based SMT, themodel (i) has the ability to memorize lexical reordering triggers, (ii) builds the search graph dynamically, and (iii) decodes with large translation units during search. The unique properties of the model are (i) its strong coupling of reordering and translation where translation and reordering decisions are conditioned on n previous translation and reordering decisions, and (ii) the ability to model local and long-range reorderings consistently. Using BLEU as a metric of translation accuracy, we found that our system performs significantly better than state-of-the-art phrase-based systems (Moses and Phrasal) and N-gram-based systems (Ncode) on standard translation tasks. We compare the reordering component of the OSM to the Moses lexical reordering model by integrating it into Moses. Our results show that OSM outperforms lexicalized reordering on all translation tasks. The translation quality is shown to be improved further by learning generalized representations with a POS-based OSM.

Original languageEnglish
Pages (from-to)157-186
Number of pages30
JournalComputational Linguistics
Volume41
Issue number2
DOIs
Publication statusPublished - 19 Jun 2015

Fingerprint

Statistical Machine Translation
N-gram
ability
remedies
learning
Translation Units
Graph
Trigger
Machine Translation
Segmentation
Translation Process
segmentation

ASJC Scopus subject areas

  • Computer Science Applications
  • Artificial Intelligence
  • Linguistics and Language
  • Language and Linguistics

Cite this

The operation sequencemodel—combining N-gram-based and phrase-based statistical machine translation. / Durrani, Nadir; Schmid, Helmut; Fraser, Alexander; Koehn, Philipp; Schütze, Hinrich.

In: Computational Linguistics, Vol. 41, No. 2, 19.06.2015, p. 157-186.

Research output: Contribution to journalArticle

Durrani, Nadir ; Schmid, Helmut ; Fraser, Alexander ; Koehn, Philipp ; Schütze, Hinrich. / The operation sequencemodel—combining N-gram-based and phrase-based statistical machine translation. In: Computational Linguistics. 2015 ; Vol. 41, No. 2. pp. 157-186.
@article{4d14547bf3944e49be0949d0d296a601,
title = "The operation sequencemodel—combining N-gram-based and phrase-based statistical machine translation",
abstract = "In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on minimal translation units, (ii) takes both source and target information into account, (iii) does not make a phrasal independence assumption, and (iv) avoids the spurious phrasal segmentation problem. As in phrase-based SMT, themodel (i) has the ability to memorize lexical reordering triggers, (ii) builds the search graph dynamically, and (iii) decodes with large translation units during search. The unique properties of the model are (i) its strong coupling of reordering and translation where translation and reordering decisions are conditioned on n previous translation and reordering decisions, and (ii) the ability to model local and long-range reorderings consistently. Using BLEU as a metric of translation accuracy, we found that our system performs significantly better than state-of-the-art phrase-based systems (Moses and Phrasal) and N-gram-based systems (Ncode) on standard translation tasks. We compare the reordering component of the OSM to the Moses lexical reordering model by integrating it into Moses. Our results show that OSM outperforms lexicalized reordering on all translation tasks. The translation quality is shown to be improved further by learning generalized representations with a POS-based OSM.",
author = "Nadir Durrani and Helmut Schmid and Alexander Fraser and Philipp Koehn and Hinrich Sch{\"u}tze",
year = "2015",
month = "6",
day = "19",
doi = "10.1162/COLI_a_00218",
language = "English",
volume = "41",
pages = "157--186",
journal = "Computational Linguistics",
issn = "0891-2017",
publisher = "MIT Press Journals",
number = "2",

}

TY - JOUR

T1 - The operation sequencemodel—combining N-gram-based and phrase-based statistical machine translation

AU - Durrani, Nadir

AU - Schmid, Helmut

AU - Fraser, Alexander

AU - Koehn, Philipp

AU - Schütze, Hinrich

PY - 2015/6/19

Y1 - 2015/6/19

N2 - In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on minimal translation units, (ii) takes both source and target information into account, (iii) does not make a phrasal independence assumption, and (iv) avoids the spurious phrasal segmentation problem. As in phrase-based SMT, themodel (i) has the ability to memorize lexical reordering triggers, (ii) builds the search graph dynamically, and (iii) decodes with large translation units during search. The unique properties of the model are (i) its strong coupling of reordering and translation where translation and reordering decisions are conditioned on n previous translation and reordering decisions, and (ii) the ability to model local and long-range reorderings consistently. Using BLEU as a metric of translation accuracy, we found that our system performs significantly better than state-of-the-art phrase-based systems (Moses and Phrasal) and N-gram-based systems (Ncode) on standard translation tasks. We compare the reordering component of the OSM to the Moses lexical reordering model by integrating it into Moses. Our results show that OSM outperforms lexicalized reordering on all translation tasks. The translation quality is shown to be improved further by learning generalized representations with a POS-based OSM.

AB - In this article, we present a novel machine translation model, the Operation Sequence Model (OSM), which combines the benefits of phrase-based and N-gram-based statistical machine translation (SMT) and remedies their drawbacks. The model represents the translation process as a linear sequence of operations. The sequence includes not only translation operations but also reordering operations. As in N-gram-based SMT, the model is: (i) based on minimal translation units, (ii) takes both source and target information into account, (iii) does not make a phrasal independence assumption, and (iv) avoids the spurious phrasal segmentation problem. As in phrase-based SMT, themodel (i) has the ability to memorize lexical reordering triggers, (ii) builds the search graph dynamically, and (iii) decodes with large translation units during search. The unique properties of the model are (i) its strong coupling of reordering and translation where translation and reordering decisions are conditioned on n previous translation and reordering decisions, and (ii) the ability to model local and long-range reorderings consistently. Using BLEU as a metric of translation accuracy, we found that our system performs significantly better than state-of-the-art phrase-based systems (Moses and Phrasal) and N-gram-based systems (Ncode) on standard translation tasks. We compare the reordering component of the OSM to the Moses lexical reordering model by integrating it into Moses. Our results show that OSM outperforms lexicalized reordering on all translation tasks. The translation quality is shown to be improved further by learning generalized representations with a POS-based OSM.

UR - http://www.scopus.com/inward/record.url?scp=84931038728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84931038728&partnerID=8YFLogxK

U2 - 10.1162/COLI_a_00218

DO - 10.1162/COLI_a_00218

M3 - Article

AN - SCOPUS:84931038728

VL - 41

SP - 157

EP - 186

JO - Computational Linguistics

JF - Computational Linguistics

SN - 0891-2017

IS - 2

ER -