Pivot language approach for phrase-based statistical machine translation

This paper proposes a novel method for phrase-based statistical machine translation based on the use of a pivot language. To translate between languages Ls and Lt with limited bilingual resources, we bring in a third language, L p, called the pivot language. For the language pairs Ls − L p and L p − Lt, there exist large bilingual corpora. Using only Ls − L p and L p − Lt bilingual corpora, we can build a translation model for Ls − Lt. The advantage of this method lies in the fact that we can perform translation between Ls and Lt even if there is no bilingual corpus available for this language pair. Using BLEU as a metric, our pivot language approach significantly outperforms the standard model trained on a small bilingual corpus. Moreover, with a small Ls − Lt bilingual corpus available, our method can further improve translation quality by using the additional Ls − L p and L p − Lt bilingual corpora.

[1]  Hermann Ney,et al.  The Alignment Template Approach to Statistical Machine Translation , 2004, CL.

[2]  Philip Resnik,et al.  Word-Based Alignment, Phrase-Based Translation: What’s the Link? , 2006, AMTA.

[3]  David Yarowsky,et al.  Inducing Translation Lexicons via Diverse Similarity Measures and Bridge Languages , 2002, CoNLL.

[4]  Philipp Koehn,et al.  Pharaoh: A Beam Search Decoder for Phrase-Based Statistical Machine Translation Models , 2004, AMTA.

[5]  Kevin Knight,et al.  A Syntax-based Statistical Translation Model , 2001, ACL.

[6]  Joel D. Martin,et al.  Word Alignment for Languages with Scarce Resources , 2005, ParallelText@ACL.

[7]  Mark Sanderson,et al.  Improving Cross Language Information Retrieval with Triangulated Translation. , 2001, SIGIR 2002.

[8]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[9]  Dekai Wu,et al.  Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora , 1997, CL.

[10]  Philipp Koehn,et al.  Manual and Automatic Evaluation of Machine Translation between European Languages , 2006, WMT@HLT-NAACL.

[11]  Noah A. Smith,et al.  The Web as a Parallel Corpus , 2003, CL.

[12]  Hua Wu,et al.  Word Alignment for Languages with Scarce Resources Using Bilingual Corpora of Other Language Pairs , 2006, ACL.

[13]  Robert J. Gaizauskas,et al.  Aligning Words in English-Hindi Parallel Corpora , 2005, ParallelText@ACL.

[14]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[15]  Philipp Koehn,et al.  Europarl: A Parallel Corpus for Statistical Machine Translation , 2005, MTSUMMIT.

[16]  Philipp Koehn,et al.  Improved Statistical Machine Translation Using Paraphrases , 2006, NAACL.

[17]  Tetsuya Sakai,et al.  Toshiba BRIDJE at NTCIR-4 CLIR: Monolingual/Bilingual IR and Flexible Feedback , 2004, NTCIR.

[18]  Chris Quirk,et al.  Dependency Treelet Translation: Syntactically Informed Phrasal SMT , 2005, ACL.

[19]  Andy Way,et al.  A Syntactic Skeleton for Statistical Machine Translation , 2006, EAMT.

[20]  Philip Resnik,et al.  An Unsupervised Method for Word Sense Tagging using Parallel Corpora , 2002, ACL.

[21]  Lars Borin.  You'll Take the High Road and I'll Take the Low Road: Using a Third Language to Improve Bilingual Word Alignment , 2000, COLING.

[22]  Marti A. Hearst,et al.  HLT-NAACL 2003 : Human Language Technology conference of the North American Chapter of the Association for Computational Linguistics : proceedings of the main conference : May 27 to June 1, 2003, Edmonton, Alberta, Canada , 2003 .

[23]  Srinivas Bangalore,et al.  Learning Dependency Translation Models as Collections of Finite-State Head Transducers , 2000, Computational Linguistics.

[24]  Stella Markantonatou,et al.  METIS-II: Machine Translation for Low Resource Languages , 2006, LREC.

[25]  I. Dan Melamed,et al.  Statistical Machine Translation by Parsing , 2004, ACL.

[26]  Noriko Kando,et al.  Two-Stage Refinement of Query Translation in a Pivot Language Approach to Cross-Lingual Information Retrieval: An Experiment at CLEF 2003 , 2003, CLEF.

[27]  Philip Resnik,et al.  Improved HMM Alignment Models for Languages with Scarce Resources , 2005, ParallelText@ACL.

[28]  Hermann Ney,et al.  Discriminative Training and Maximum Entropy Models for Statistical Machine Translation , 2002, ACL.

[29]  Hermann Ney,et al.  Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information , 2004, CL.

[30]  Robert L. Mercer,et al.  The Mathematics of Statistical Machine Translation: Parameter Estimation , 1993, CL.

[31]  Hitoshi Isahara,et al.  A Comparison of Pivot Methods for Phrase-Based Statistical Machine Translation , 2007, NAACL.

[32]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[33]  Mark Sanderson,et al.  Improving cross language retrieval with triangulated translation , 2001, SIGIR '01.

[34]  David Chiang,et al.  A Hierarchical Phrase-Based Model for Statistical Machine Translation , 2005, ACL.

[35]  Dan Tufis,et al.  Combined Word Alignments , 2005, ParallelText@ACL.