Interlocking Phrases in Phrase-based Statistical Machine Translation

This paper presents an study of the use of interlocking phrases in phrase-based statistical machine translation. We examine the effect on translation quality when the translation units used in the translation hypotheses are allowed to overlap on the source side, on the target side and on both sides. A large-scale evaluation on 380 language pairs was conducted. Our results show that overall the use of overlapping phrases improved translation quality by 0.3 BLEU points on average. Further analysis revealed that language pairs requiring a larger amount of re-ordering benefited the most from our approach. When the evaluation was restricted to such pairs, the average improvement increased to up to 0.75 BLEU points with over 97% of the pairs improving. Our approach requires only a simple modification to the decoding algorithm and we believe it should be generally applicable to improve the performance of phrase-based decoders.

[1]  S. Riezler,et al.  Offline extraction of overlapping phrases for hierarchical phrase-based translation , 2014, IWSLT.

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

[3]  S. Vogel,et al.  Overlapping phrase-level translation rules in an SMT engine , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

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

[5]  Christoph Tillmann,et al.  A Unigram Orientation Model for Statistical Machine Translation , 2004, NAACL.

[6]  Matti Kääriäinen.  Sinuhe - Statistical Machine Translation using a Globally Trained Conditional Exponential Family Translation Model , 2009, EMNLP.

[7]  Eiichiro Sumita,et al.  Creating corpora for speech-to-speech translation , 2003, INTERSPEECH.

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

[9]  Alexandra Birch,et al.  Reordering metrics for statistical machine translation , 2011 .

[10]  Vladimir Eidelman,et al.  cdec: A Decoder, Alignment, and Learning Framework for Finite- State and Context-Free Translation Models , 2010, ACL.

[11]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

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

[13]  Philipp Koehn,et al.  Edinburgh’s Submission to all Tracks of the WMT 2009 Shared Task with Reordering and Speed Improvements to Moses , 2009, WMT@EACL.

[14]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[15]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[16]  Wolfgang Macherey,et al.  Lattice-based Minimum Error Rate Training for Statistical Machine Translation , 2008, EMNLP.

[17]  Andrew McCallum,et al.  Machine Translation Using Overlapping Alignments and SampleRank , 2009 .

[18]  Hermann Ney,et al.  Improved Statistical Alignment Models , 2000, ACL.