Training of Phrase Based Models
The fundamental data structure in phrase based models is a table of phrase pairs with associated scores which may come from probability distributions. Most commonly, this table is acquired from a word aligned parallel corpus.
Phrase Based Model Training is the main subject of 31 publications. 22 are discussed here.
Publications
Several methods to extract phrases from a parallel corpus have been proposed. Most make the use of word alignments
Tillmann, Christoph (2003):
A Projection Extension Algorithm for Statistical Machine Translation, Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing
@inproceedings{Tillmann:2003,
author = {Tillmann, Christoph},
title = {A Projection Extension Algorithm for Statistical Machine Translation},
booktitle = {Proceedings of the 2003 Conference on Empirical Methods in Natural Language Processing},
editor = {Michael Collins and Mark Steedman},
url = {
http://www.aclweb.org/anthology/W03-1001.pdf},
pages = {1--8},
year = 2003
}
(Tillmann, 2003;
Ying Zhang and Stephan Vogel and Alex Waibel (2003):
Integrated Phrase Segmentation and Alignment Algorithm for Statistical Machine Translation, Proceedings of International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE'03)
@inproceedings{Zhang:2003,
author = {Ying Zhang and Stephan Vogel and Alex Waibel},
title = {Integrated Phrase Segmentation and Alignment Algorithm for Statistical Machine Translation},
booktitle = {Proceedings of International Conference on Natural Language Processing and Knowledge Engineering (NLP-KE'03)},
address = {Beijing, China},
year = 2003
}
Zhang et al., 2003;
Zhao, Bing and Vogel, Stephan (2005):
A Generalized Alignment-Free Phrase Extraction, Proceedings of the ACL Workshop on Building and Using Parallel Texts
@InProceedings{zhao-vogel:2005:WPT,
author = {Zhao, Bing and Vogel, Stephan},
title = {A Generalized Alignment-Free Phrase Extraction},
booktitle = {Proceedings of the ACL Workshop on Building and Using Parallel Texts},
month = {June},
address = {Ann Arbor, Michigan},
publisher = {Association for Computational Linguistics},
pages = {141--144},
url = {
http://www.aclweb.org/anthology/W/W05/W05-0825},
year = 2005
}
Zhao and Vogel, 2005;
Zhang, Ying and Vogel, Stephan (2005):
Competitive Grouping in Integrated Phrase Segmentation and Alignment Model, Proceedings of the ACL Workshop on Building and Using Parallel Texts
@InProceedings{zhang-vogel:2005:WPT,
author = {Zhang, Ying and Vogel, Stephan},
title = {Competitive Grouping in Integrated Phrase Segmentation and Alignment Model},
booktitle = {Proceedings of the ACL Workshop on Building and Using Parallel Texts},
month = {June},
address = {Ann Arbor, Michigan},
publisher = {Association for Computational Linguistics},
pages = {159--162},
url = {
http://www.aclweb.org/anthology/W/W05/W05-0829},
year = 2005
}
Zhang and Vogel, 2005;
Hendra Setiawan and Haizhou Li and Min Zhang (2005):
Learning Phrase Translation using Level of Detail Approach, Proceedings of the Tenth Machine Translation Summit (MT Summit X)
@InProceedings{Setiawan:2005:MTS,
author = {Hendra Setiawan and Haizhou Li and Min Zhang},
title = {Learning Phrase Translation using Level of Detail Approach},
booktitle = {Proceedings of the Tenth Machine Translation Summit (MT Summit X)},
month = {September},
address = {Phuket, Thailand},
year = 2005
}
Setiawan et al., 2005). One may restrict extraction of phrase pairs to the smallest phrases that cover the sentence
José B. Mariño and Rafael E. Banchs and Josep M. Crego and Adrià de Gispert and Patrik Lambert and José A. R. Fonollosa and Marta Ruiz Costa-jussà (2005):
Bilingual N-gram Statistical Machine Translation, Proceedings of the Tenth Machine Translation Summit (MT Summit X)
@InProceedings{Marino:2005:MTS,
author = {Jos\'{e} B. Mari{\~n}o and Rafael E. Banchs and Josep M. Crego and Adri\`{a} de Gispert and Patrik Lambert and Jos\'{e} A. R. Fonollosa and Marta Ruiz Costa-juss\`{a}},
title = {Bilingual N-gram Statistical Machine Translation},
url = {
http://mi.eng.cam.ac.uk/~ad465/agispert/docs/papers/275-282\_10\_Paper.pdf},
googlescholar = {13481314314109470752},
booktitle = {Proceedings of the Tenth Machine Translation Summit (MT Summit X)},
month = {September},
address = {Phuket, Thailand},
year = 2005
}
(Mariño et al., 2005).
Patrik Lambert and Rafael E. Banchs (2005):
Data Inferred Multi-word Expressions for Statistical Machine Translation, Proceedings of the Tenth Machine Translation Summit (MT Summit X)
@InProceedings{Lambert:2005:MTS,
author = {Patrik Lambert and Rafael E. Banchs},
title = {Data Inferred Multi-word Expressions for Statistical Machine Translation},
url = {
http://hal.archives-ouvertes.fr/docs/00/70/50/07/PDF/05\_data\_mwe\_mtsummit.pdf},
googlescholar = {9597266194439702371},
booktitle = {Proceedings of the Tenth Machine Translation Summit (MT Summit X)},
month = {September},
address = {Phuket, Thailand},
year = 2005
}
Lambert and Banchs (2005) compare this restrictive method with the method described in this book and proposes some refinements.
Phrase alignment may be carried out directly from sentence-aligned corpora using a probabilistic model
Jung H. Shin and Young S. Han and Key-Sun Choi (1996):
Bilingual Knowledge Acquisition from Korean-English Parallel Corpus Using Alignment, Proceedings of the 16th International Conference on Computational Linguistics (COLING)
@InProceedings{Shin:1996,
author = {Jung H. Shin and Young S. Han and Key-Sun Choi},
title = {Bilingual Knowledge Acquisition from {Korean-English} Parallel Corpus Using Alignment},
url = {
http://acl.ldc.upenn.edu/C/C96/C96-1040.pdf},
googlescholar = {16730902637563039604},
booktitle = {Proceedings of the 16th International Conference on Computational Linguistics (COLING)},
year = 1996
}
(Shin et al., 1996), pattern mining methods
Kaoru Yamamoto and Taku Kudo and Yuta Tsuboi and Yuji Matsumoto (2003):
Learning Sequence-to-Sequence Correspondences from Parallel Corpora via Sequential Pattern Mining, HLT-NAACL 2003 Workshop: Building and Using Parallel Texts: Data Driven Machine Translation and Beyond
@inproceedings{Yamamoto:2003,
author = {Kaoru Yamamoto and Taku Kudo and Yuta Tsuboi and Yuji Matsumoto },
title = {Learning Sequence-to-Sequence Correspondences from Parallel Corpora via Sequential Pattern Mining},
url = {
http://acl.ldc.upenn.edu/W/W03/W03-0314.pdf},
googlescholar = {3080371715917059705},
booktitle = {HLT-NAACL 2003 Workshop: Building and Using Parallel Texts: Data Driven Machine Translation and Beyond},
editor = {Rada Mihalcea and Ted Pedersen},
month = {May 31},
address = {Edmonton, Alberta, Canada},
publisher = {Association for Computational Linguistics},
year = 2003
}
(Yamamoto et al., 2003), or using matrix factorization
Goutte, Cyril and Yamada, Kenji and Gaussier, Eric (2004):
Aligning words using matrix factorisation, Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL'04), Main Volume
@inproceedings{Goutte:2004,
author = {Goutte, Cyril and Yamada, Kenji and Gaussier, Eric},
title = {Aligning words using matrix factorisation},
url = {
http://acl.ldc.upenn.edu/acl2004/main/pdf/187\_pdf\_2-col.pdf},
booktitle = {Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL'04), Main Volume},
month = {July},
address = {Barcelona, Spain},
pages = {502--509},
year = 2004
}
(Goutte et al., 2004). IBM Model 1 probabilities may be used to separate word aligned to each phrase against words outside it
Stephan Vogel (2005):
PESA: Phrase Pair Extraction as Sentence Splitting, Proceedings of the Tenth Machine Translation Summit (MT Summit X)
@InProceedings{Vogel:2005:MTS,
author = {Stephan Vogel},
title = {{PESA}: Phrase Pair Extraction as Sentence Splitting},
url = {
http://mt-archive.info/MTS-2005-Vogel.pdf},
googlescholar = {15595365670474652682},
booktitle = {Proceedings of the Tenth Machine Translation Summit (MT Summit X)},
month = {September},
address = {Phuket, Thailand},
year = 2005
}
(Vogel, 2005) — a method also used for splitting long sentences
Jia Xu and Richard Zens and Hermann Ney (2005):
Sentence segmentation using IBM word alignment model 1, Proceedings of the 10th Conference of the European Association for Machine Translation (EAMT)
@InProceedings{Xu:2005:EAMT,
author = {Jia Xu and Richard Zens and Hermann Ney},
title = {Sentence segmentation using IBM word alignment model 1},
url = {
http://www-i6.informatik.rwth-aachen.de/~zens/publications/Xu+Zens+Ney\_SentenceSegmentationUsingIBMWordAlignmentModel1\_EAMT\_2005.pdf},
googlescholar = {11994205578764013029},
booktitle = {Proceedings of the 10th Conference of the European Association for Machine Translation (EAMT)},
month = {May},
address = {Budapest},
year = 2005
}
(Xu et al., 2005).
Zhao, Bing and Vogel, Stephan and Eck, Matthias and Waibel, Alex (2004):
Phrase Pair Rescoring with Term Weighting for Statistical Machine Translation, Proceedings of EMNLP 2004
@inproceedings{Zhao:2004b,
author = {Zhao, Bing and Vogel, Stephan and Eck, Matthias and Waibel, Alex},
title = {Phrase Pair Rescoring with Term Weighting for Statistical Machine Translation},
booktitle = {Proceedings of EMNLP 2004},
editor = {Dekang Lin and Dekai Wu},
month = {July},
address = {Barcelona, Spain},
publisher = {Association for Computational Linguistics},
pages = {206--213},
year = 2004
}
Zhao et al. (2004) use a measure based on the td-idf score from information retrieval to score phrase translations. Additional feature scores may be also used during the parameter tuning of the decoder to determine which phrase pairs should be discarded
Deng, Yonggang and Xu, Jia and Gao, Yuqing (2008):
Phrase Table Training for Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?, Proceedings of ACL-08: HLT
@InProceedings{deng-xu-gao:2008:ACLMain,
author = {Deng, Yonggang and Xu, Jia and Gao, Yuqing},
title = {Phrase Table Training for Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?},
booktitle = {Proceedings of ACL-08: HLT},
month = {June},
address = {Columbus, Ohio},
publisher = {Association for Computational Linguistics},
pages = {81--88},
url = {
http://www.aclweb.org/anthology/P/P08/P08-1010},
year = 2008
}
(Deng et al., 2008).
Jae Dong Kim and Stephan Vogel (2007):
Iterative refinement of lexicon and phrasal alignment, Proceedings of the MT Summit XI
@inproceedings{Kim:2007:MTSummit,
author = {Jae Dong Kim and Stephan Vogel},
title = {Iterative refinement of lexicon and phrasal alignment},
url = {
http://www.mt-archive.info/MTS-2007-Kim.pdf},
googlescholar = {7053948382831847545},
booktitle = {Proceedings of the {MT} Summit XI},
year = 2007
}
Kim and Vogel (2007) use an iterative method that adds extracted phrases to the parallel corpus to bootstrap better alignments and extract better phrases.
Turchi, Marco and De Bie, Tijl and Cristianini, Nello (2008):
Learning Performance of a Machine Translation System: a Statistical and Computational Analysis, Proceedings of the Third Workshop on Statistical Machine Translation
@InProceedings{turchi-debie-cristianini:2008:WMT,
author = {Turchi, Marco and De Bie, Tijl and Cristianini, Nello},
title = {Learning Performance of a Machine Translation System: a Statistical and Computational Analysis},
booktitle = {Proceedings of the Third Workshop on Statistical Machine Translation},
month = {June},
address = {Columbus, Ohio},
publisher = {Association for Computational Linguistics},
pages = {35--43},
url = {
http://www.aclweb.org/anthology/W/W08/W08-0305},
year = 2008
}
Turchi et al. (2008) give an overall analysis of the learning problem for phrase-based machine translation.
Word alignment probabilities may guide decisions on phrase extraction and phrase scoring.
Ashish Venugopal and Andreas Zollmann and Noah A. Smith and Stephan Vogel (2008):
Wider Pipelines: N-Best Alignments and Parses in MT Training, Proceedings of the Eighth Conference of the Association for Machine Translation in the Americas (AMTA)
@inproceedings{amta08:Venugopal,
author = {Ashish Venugopal and Andreas Zollmann and Noah A. Smith and Stephan Vogel},
title = {Wider Pipelines: N-Best Alignments and Parses in {MT} Training},
url = {
http://www.mt-archive.info/AMTA-2008-Venugopal.pdf},
googlescholar = {9994624296928116484},
pages = {192--201},
booktitle = {Proceedings of the Eighth Conference of the Association for Machine Translation in the Americas (AMTA)},
location = {Waikiki, Hawaii},
year = 2008
}
Venugopal et al. (2008) use posterior probabilities and
Nadi Tomeh and Alexandre Allauzen and François Yvon (2011):
Discriminative Weighted Alignment Matrices For Statistical Machine Translation, Proceedings of the 15th International Conference of the European Association for Machine Translation (EAMT)
@inproceedings{eamt11:Tomeh,
author = {Nadi Tomeh and Alexandre Allauzen and Fran{\,c}ois Yvon},
title = {Discriminative Weighted Alignment Matrices For Statistical Machine Translation},
pages = {305-312},
booktitle = {Proceedings of the 15th International Conference of the European Association for Machine Translation (EAMT)},
location = {Leuven, Belgium},
editor = {Mikel L. Forcada and Heidi Depraetere and Vincent Vandeghinste},
url = {
http://www.mt-archive.info/EAMT-2011-Tomeh.pdf},
year = 2011
}
(Tomeh et al., 2011) use discriminative trained word alignment confidence scores.
Existing bilingual dictionaries may be simply added as additional parallel data to the training data. This may, however, miss the right context in which these words occur.
Hideo Okuma and Hirofumi Yamamoto and Eiichiro Sumita (2007):
Introducing Translation Dictionary Into Phrase-based SMT, Proceedings of the MT Summit XI
@inproceedings{Okuma:2007:MTSummit,
author = {Hideo Okuma and Hirofumi Yamamoto and Eiichiro Sumita},
title = {Introducing Translation Dictionary Into Phrase-based {SMT}},
url = {
http://mt-archive.info/MTS-2007-Okuma.pdf},
googlescholar = {3626188979102133542},
booktitle = {Proceedings of the {MT} Summit XI},
year = 2007
}
Okuma et al. (2007) propose to insert phrases into the phrase tables that adapt existing entries with a very similar word to the dictionary word by replacing it with the dictionary word.
A stream of new training data may be added continuously to an existing translation model, requiring fast incremental updating with the use of a variant of the online EM algorithm
Ortiz-Martínez, Daniel and García-Varea, Ismael and Casacuberta, Francisco (2010):
Online Learning for Interactive Statistical Machine Translation, Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
mentioned in Phrase Based Model Training and Incremental Updating@InProceedings{ortizmartinez-garciavarea-casacuberta:2010:NAACLHLT,
author = {Ortiz-Mart\'{i}nez, Daniel and Garc\'{i}a-Varea, Ismael and Casacuberta, Francisco},
title = {Online Learning for Interactive Statistical Machine Translation},
booktitle = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
month = {June},
address = {Los Angeles, California},
publisher = {Association for Computational Linguistics},
pages = {546--554},
url = {
http://www.aclweb.org/anthology/N10-1079},
year = 2010
}
(Ortiz-Martínez et al., 2010) and dynamic
suffix arrays Levenberg, Abby and Callison-Burch, Chris and Osborne, Miles (2010):
Stream-based Translation Models for Statistical Machine Translation, Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
mentioned in Phrase Based Model Training and Incremental Updating@InProceedings{levenberg-callisonburch-osborne:2010:NAACLHLT,
author = {Levenberg, Abby and Callison-Burch, Chris and Osborne, Miles},
title = {Stream-based Translation Models for Statistical Machine Translation},
booktitle = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
month = {June},
address = {Los Angeles, California},
publisher = {Association for Computational Linguistics},
pages = {394--402},
url = {
http://www.aclweb.org/anthology/N10-1062},
year = 2010
}
(Levenberg et al., 2010).
With the increasing size of available parallel corpora and translation models, efficient use of working memory becomes an issue, motivating the development of parallel infrastructures for training such as Google's MapReduce
Dyer, Christopher J. and Cordova, Aaron and Mont, Alex and Lin, Jimmy (2008):
Fast, Easy, and Cheap: Construction of Statistical Machine Translation Models with MapReduce, Proceedings of the Third Workshop on Statistical Machine Translation
@InProceedings{dyer-EtAl:2008:WMT,
author = {Dyer, Christopher J. and Cordova, Aaron and Mont, Alex and Lin, Jimmy},
title = {Fast, Easy, and Cheap: Construction of Statistical Machine Translation Models with {MapReduce}},
booktitle = {Proceedings of the Third Workshop on Statistical Machine Translation},
month = {June},
address = {Columbus, Ohio},
publisher = {Association for Computational Linguistics},
pages = {199--207},
url = {
http://www.aclweb.org/anthology/W/W08/W08-0333},
year = 2008
}
(Dyer et al., 2008).
Benchmarks
Discussion
Related Topics
New Publications
He, Hua and Lin, Jimmy and Lopez, Adam (2013):
Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs, Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
@InProceedings{he-lin-lopez:2013:NAACL-HLT,
author = {He, Hua and Lin, Jimmy and Lopez, Adam},
title = {Massively Parallel Suffix Array Queries and On-Demand Phrase Extraction for Statistical Machine Translation Using GPUs},
booktitle = {Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
month = {June},
address = {Atlanta, Georgia},
publisher = {Association for Computational Linguistics},
pages = {325--334},
url = {
http://www.aclweb.org/anthology/N13-1033},
year = 2013
}
He et al. (2013)
Saab Mansour and Herman Ney (2014):
Translation model based weighting for phrase extraction, Proceedings of 17th Annual conference of the European Association for Machine Translation
@inproceedings{eamt-2014-Mansour,
author = {Saab Mansour and Herman Ney},
title = {Translation model based weighting for phrase extraction},
booktitle = {Proceedings of 17th Annual conference of the European Association for Machine Translation},
pages = {35-43},
url = {
http://www.mt-archive.info/10/EAMT-2014-Mansour.pdf},
location = {Dubrovnik, Croatia},
year = 2014
}
Mansour and Ney (2014)
Nadi Tomeh and Alexandre Allauzen and François Yvon (2014):
Maximum-entropy word alignment and posterior-based phrase extraction for machine translation, Machine Translation
@article{MTJ:2014:Tomeh,
author = {Nadi Tomeh and Alexandre Allauzen and Fran{\,c}ois Yvon},
title = {Maximum-entropy word alignment and posterior-based phrase extraction for machine translation},
pages = {19-56},
journal = {Machine Translation},
volume = {28},
number = {1},
month = {March},
year = 2014
}
Tomeh et al. (2014)
Kevin Flanagan (2014):
Bilingual phrase-to-phrase alignment for arbitrarily-small datasets, Proceedings of the Eleventh Conference of the Association for Machine Translation in the Americas (AMTA)
@inproceedings{AMTA-2014--Flanagan,
author = {Kevin Flanagan},
title = {Bilingual phrase-to-phrase alignment for arbitrarily-small datasets},
pages = {83-95},
url = {
http://www.mt-archive.info/10/AMTA-2014--Flanagan.pdf},
volume = {1},
booktitle = {Proceedings of the Eleventh Conference of the Association for Machine Translation in the Americas (AMTA)},
location = {Vancouver, BC, Canada},
year = 2014
}
Flanagan (2014)
Kevin Flanagan (2014):
Bilingual phrase-to-phrase alignment for arbitrarily-small datasets, Proceedings of the Eleventh Conference of the Association for Machine Translation in the Americas (AMTA)
@inproceedings{AMTA-2014--Flanagan,
author = {Kevin Flanagan},
title = {Bilingual phrase-to-phrase alignment for arbitrarily-small datasets},
pages = {83-95},
url = {
http://www.mt-archive.info/10/AMTA-2014--Flanagan.pdf},
volume = {1},
booktitle = {Proceedings of the Eleventh Conference of the Association for Machine Translation in the Americas (AMTA)},
location = {Vancouver, BC, Canada},
year = 2014
}
Flanagan (2014)
Wuebker, Joern and Ney, Hermann (2013):
Length-Incremental Phrase Training for SMT, Proceedings of the Eighth Workshop on Statistical Machine Translation
@InProceedings{wuebker-ney:2013:WMT,
author = {Wuebker, Joern and Ney, Hermann},
title = {Length-Incremental Phrase Training for {SMT}},
booktitle = {Proceedings of the Eighth Workshop on Statistical Machine Translation},
month = {August},
address = {Sofia, Bulgaria},
publisher = {Association for Computational Linguistics},
pages = {309--319},
url = {
http://www.aclweb.org/anthology/W13-2238},
year = 2013
}
Wuebker and Ney (2013)
Ankit Srivastava and Andy Way (2009):
Using Percolated Dependencies for Phrase Extraction in SMT, Proceedings of the Twelfth Machine Translation Summit (MT Summit XII)
mentioned in Phrase Based Model Training and Parallel Treebanks@inproceedings{MTS09:Srivastava,
author = {Ankit Srivastava and Andy Way},
title = {Using Percolated Dependencies for Phrase Extraction in {SMT}},
url = {
http://doras.dcu.ie/15152/1/SrivastavaWay\_mts\_09.pdf},
googlescholar = {11366049404327383407},
booktitle = {Proceedings of the Twelfth Machine Translation Summit (MT Summit XII)},
publisher = {International Association for Machine Translation},
location = {Ottawa, Ontario, Canada},
year = 2009
}
Srivastava and Way (2009)
Mridul Gupta and Sanjika Hewavitharana and Stephan Vogel (2011):
Extending a probabilistic phrase alignment approach for SMT, Proceedings of the seventh International Workshop on Spoken Language Translation (IWSLT)
@inproceedings{iwslt11:Gupta,
author = {Mridul Gupta and Sanjika Hewavitharana and Stephan Vogel},
title = {Extending a probabilistic phrase alignment approach for {SMT}},
url = {
http://www.mt-archive.info/IWSLT-2011-Gupta.pdf},
pages = {175-182},
editor = {Marcello Federico and Mei-Yuh Hwang and Margit R{\"o}dder and Sebastian St{\"u}ker},
booktitle = {Proceedings of the seventh International Workshop on Spoken Language Translation (IWSLT)},
location = {San Francisco, USA},
year = 2011
}
Gupta et al. (2011)
Boxing Chen and George Foster and Roland Kuhn (2009):
Phrase Translation Model Enhanced with Association based Features, Proceedings of the Twelfth Machine Translation Summit (MT Summit XII)
@inproceedings{MTS09:Chen,
author = {Boxing Chen and George Foster and Roland Kuhn},
title = {Phrase Translation Model Enhanced with Association based Features},
url = {
http://www.mt-archive.info/MTS-2009-Chen.pdf},
googlescholar = {16816990626962163720},
booktitle = {Proceedings of the Twelfth Machine Translation Summit (MT Summit XII)},
publisher = {International Association for Machine Translation},
location = {Ottawa, Ontario, Canada},
year = 2009
}
Chen et al. (2009)
Francisco Guzman and Qin Gao and Stephan Vogel (2009):
Reassessment of the Role of Phrase Extraction in PBSMT, Proceedings of the Twelfth Machine Translation Summit (MT Summit XII)
@inproceedings{MTS09:Guzman,
author = {Francisco Guzman and Qin Gao and Stephan Vogel},
title = {Reassessment of the Role of Phrase Extraction in {PBSMT}},
url = {
http://www.mt-archive.info/MTS-2009-Guzman.pdf},
googlescholar = {3178600509478785340},
booktitle = {Proceedings of the Twelfth Machine Translation Summit (MT Summit XII)},
publisher = {International Association for Machine Translation},
location = {Ottawa, Ontario, Canada},
year = 2009
}
Guzman et al. (2009)