Article

Free access

Do we need phrases?: challenging the conventional wisdom in statistical machine translation

Authors:

Arul MenezesAuthors Info & Claims

HLT-NAACL '06: Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics

Pages 9 - 16

https://doi.org/10.3115/1220835.1220837

Published: 04 June 2006 Publication History

Abstract

We begin by exploring theoretical and practical issues with phrasal SMT, several of which are addressed by syntax-based SMT. Next, to address problems not handled by syntax, we propose the concept of a Minimal Translation Unit (MTU) and develop MTU sequence models. Finally we incorporate these models into a syntax-based SMT system and demonstrate that it improves on the state of the art translation quality within a theoretically more desirable framework.

References

[1]

Banchs, Rafael, Joseph Crego, Adrià de Gispert, Patrik Lambert, and Jose Mariño. 2005. Statistical machine translation of Euparl data by using bilingual n-grams. In Proceedings of ACL Workshop on Building and Using Parallel Texts.

Digital Library

[2]

Brown, Peter, Vincent Della Pietra, Stephen Della Pietra, and Robert Mercer. 1993. The mathematics of statistical machine translation: parameter estimation. Computational Linguistics 19(2): 263--311.

Digital Library

[3]

Callison-Burch, Chris, Colin Bannard, and Josh Schroeder. 2005. Scaling phrase-based machine translation to larger corpora and longer phrases. In Proceedings of ACL.

Digital Library

[4]

Chiang, David. 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of ACL.

Digital Library

[5]

Heidorn, George. 2000. "Intelligent writing assistance". In Dale et al. Handbook of Natural Language Processing, Marcel Dekker.

[6]

Koehn, Philipp, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase based translation. In Proceedings of NAACL.

Digital Library

[7]

Koehn, Philipp. 2004. Pharaoh: A beam search decoder for phrase-based statistical machine translation models. In Proceedings of AMTA.

[8]

Och, Franz Josef and Hermann Ney. 2003. A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1): 19--51.

Digital Library

[9]

Och, Franz Josef and Hermann Ney. 2004. The Alignment Template approach to statistical machine translation, Computational Linguistics, 30(4):417--450.

Digital Library

[10]

Och, Franz Josef. 2003. Minimum error rate training in statistical machine translation. In Proceedings of ACL.

Digital Library

[11]

Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of ACL.

Digital Library

[12]

Quirk, Chris and Arul Menezes. 2005. Dependency tree translation: syntactically-informed phrasal SMT. In Proceedings of ACL.

Digital Library

[13]

Stolcke, Andreas. 1998. Entropy-based pruning of backoff language models. In Proceedings of DARPA Broadcast News Transcription and Understanding.

[14]

Vogel, Stephan, Ying Zhang, Fei Huang, Alicia Tribble, Ashish Venugopal, Bing Zhao, Alex Waibel. 2003. The CMU statistical machine translation system. In Proceedings of MT Summit.

[15]

Zens, Richard, and Hermann Ney. 2003. A comparative study on reordering constraints in statistical machine translation. In Proceedings of ACL.

Digital Library

[16]

Zhang, Ying and Stephan Vogel. 2005. An efficient phrase-to-phrase alignment model for arbitrarily long phrase and large corpora. In Proceedings of EAMT.

Cited By

Nasri CSmaili KLatiri C(2014)Training Phrase-Based SMT without Explicit Word AlignmentProceedings of the 15th International Conference on Computational Linguistics and Intelligent Text Processing - Volume 840410.1007/978-3-642-54903-8_20(233-241)Online publication date: 6-Apr-2014
https://dl.acm.org/doi/10.1007/978-3-642-54903-8_20
Duan NLi MZhou MTsujii JHenderson JPasca M(2012)Forced derivation tree based model training to statistical machine translationProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning10.5555/2390948.2391002(445-454)Online publication date: 12-Jul-2012
https://dl.acm.org/doi/10.5555/2390948.2391002
Vaswani AMi HHuang LChiang DLin D(2011)Rule Markov models for fast tree-to-string translationProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 110.5555/2002472.2002580(856-864)Online publication date: 19-Jun-2011
https://dl.acm.org/doi/10.5555/2002472.2002580
Show More Cited By

Do we need phrases?: challenging the conventional wisdom in statistical machine translation
1. Computing methodologies
  1. Artificial intelligence
2. Hardware
  1. Power and energy
    1. Power estimation and optimization

Recommendations

Extending context-free grammars with permutation phrases

A permutation phrase is a grammatical phrase that specifies a syntactic construct as any permutation of a set of constituent elements. Permutation phrases allow for the concise and natural expression of free-order constructs as found in programming ...
Decoding with syntactic and non-syntactic phrases in a syntax-based machine translation system
SSST '09: Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation

A key concern in building syntax-based machine translation systems is how to improve coverage by incorporating more traditional phrase-based SMT phrase pairs that do not correspond to syntactic constituents. At the same time, it is desirable to include ...
Multi-layered pipeline parsing of phrases from multi-axiom grammars

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image DL Hosted proceedings

HLT-NAACL '06: Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics

June 2006

522 pages

General Chair:
Robert C. Moore
Microsoft Research

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 04 June 2006

Qualifiers

Article

Acceptance Rates

HLT-NAACL '06 Paper Acceptance Rate 62 of 257 submissions, 24%;

Overall Acceptance Rate 240 of 768 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

8
Total Citations
View Citations
274
Total Downloads

Downloads (Last 12 months)57
Downloads (Last 6 weeks)11

Reflects downloads up to 24 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Nasri CSmaili KLatiri C(2014)Training Phrase-Based SMT without Explicit Word AlignmentProceedings of the 15th International Conference on Computational Linguistics and Intelligent Text Processing - Volume 840410.1007/978-3-642-54903-8_20(233-241)Online publication date: 6-Apr-2014
https://dl.acm.org/doi/10.1007/978-3-642-54903-8_20
Duan NLi MZhou MTsujii JHenderson JPasca M(2012)Forced derivation tree based model training to statistical machine translationProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning10.5555/2390948.2391002(445-454)Online publication date: 12-Jul-2012
https://dl.acm.org/doi/10.5555/2390948.2391002
Vaswani AMi HHuang LChiang DLin D(2011)Rule Markov models for fast tree-to-string translationProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 110.5555/2002472.2002580(856-864)Online publication date: 19-Jun-2011
https://dl.acm.org/doi/10.5555/2002472.2002580
Jiang HLi SYang MZhao TWu DChiang D(2009)A study of translation rule classification for syntax-based statistical machine translationProceedings of the Third Workshop on Syntax and Structure in Statistical Translation10.5555/1626344.1626350(45-50)Online publication date: 5-Jun-2009
https://dl.acm.org/doi/10.5555/1626344.1626350
Schroeder JCohn TKoehn PLascarides AGardent CNivre J(2009)Word lattices for multi-source translationProceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics10.5555/1609067.1609147(719-727)Online publication date: 30-Mar-2009
https://dl.acm.org/doi/10.5555/1609067.1609147
Chen BZhang MAw A(2009)Two-Stage Hypotheses Generation for Spoken Language TranslationACM Transactions on Asian Language Information Processing (TALIP)10.1145/1482343.14823478:1(1-22)Online publication date: 1-Mar-2009
https://dl.acm.org/doi/10.1145/1482343.1482347
Lopez AScott DUszkoreit H(2008)Tera-scale translation models via pattern matchingProceedings of the 22nd International Conference on Computational Linguistics - Volume 110.5555/1599081.1599145(505-512)Online publication date: 18-Aug-2008
https://dl.acm.org/doi/10.5555/1599081.1599145
Menezes AToutanova KQuirk CKoehn PMonz C(2006)Microsoft research treelet translation systemProceedings of the Workshop on Statistical Machine Translation10.5555/1654650.1654676(158-161)Online publication date: 8-Jun-2006
https://dl.acm.org/doi/10.5555/1654650.1654676

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents