EU-BRIDGE MT: text translation of talks in the EU-BRIDGE project

EU-BRIDGE 1 is a European research project which is aimed at developing innovative speech translation technology. This paper describes one of the collaborative efforts within EUBRIDGE to further advance the state of the art in machine translation between two European language pairs, English!French and German!English. Four research institutions involved in the EU-BRIDGE project combined their individual machine translation systems and participated with a joint setup in the machine translation track of the evaluation campaign at the 2013 International Workshop on Spoken Language Translation (IWSLT). We present the methods and techniques to achieve high translation quality for text translation of talks which are applied at RWTH Aachen University, the University of Edinburgh, Karlsruhe Institute of Technology, and Fondazione Bruno Kessler. We then show how we have been able to considerably boost translation performance (as measured in terms of the metrics BLEU and TER) by means of system combination. The joint setups yield empirical gains of up to 1.4 points in BLEU and 2.8 points in TER on the IWSLT test sets compared to the best single systems.

[1]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[2]  Franz Josef Och,et al.  An Efficient Method for Determining Bilingual Word Classes , 1999, EACL.

[3]  Ralph Weischedel,et al.  A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION , 2005 .

[4]  Markus Freitag,et al.  Jane 2: Open Source Phrase-based and Hierarchical Statistical Machine Translation , 2012, COLING.

[5]  Hermann Ney,et al.  Extending Statistical Machine Translation with Discriminative and Trigger-Based Lexicon Models , 2009, EMNLP.

[6]  Jan Niehues,et al.  Discriminative Word Alignment via Alignment Matrix Modeling , 2008, WMT@ACL.

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

[8]  George F. Foster,et al.  Batch Tuning Strategies for Statistical Machine Translation , 2012, NAACL.

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

[10]  Kenneth Heafield,et al.  KenLM: Faster and Smaller Language Model Queries , 2011, WMT@EMNLP.

[11]  Markus Freitag,et al.  Joint WMT 2012 Submission of the QUAERO Project , 2012, WMT@NAACL-HLT.

[12]  Rachel Panckhurst,et al.  Traitement automatique des langues. , 2001 .

[13]  Hermann Ney,et al.  Improving Statistical Machine Translation with Word Class Models , 2013, EMNLP.

[14]  Marcello Federico.  Language Modelling , 2012 .

[15]  Philipp Koehn,et al.  Sparse lexicalised features and topic adaptation for SMT , 2012, IWSLT.

[16]  Philipp Koehn,et al.  Empirical Methods for Compound Splitting , 2003, EACL.

[17]  Nadir Durrani,et al.  A Joint Sequence Translation Model with Integrated Reordering , 2011, ACL.

[18]  Jan Niehues,et al.  Combining Word Reordering Methods on different Linguistic Abstraction Levels for Statistical Machine Translation , 2013, SSST@NAACL-HLT.

[19]  Noah A. Smith,et al.  A Simple, Fast, and Effective Reparameterization of IBM Model 2 , 2013, NAACL.

[20]  Jan Niehues,et al.  An MT Error-Driven Discriminative Word Lexicon using Sentence Structure Features , 2013, WMT@ACL.

[21]  Sebastian Stüker,et al.  Overview of the IWSLT 2012 evaluation campaign , 2012, IWSLT.

[22]  Markus Freitag,et al.  Hierarchical Phrase-Based Translation with Jane 2 , 2012, Prague Bull. Math. Linguistics.

[23]  Jan Niehues,et al.  A POS-Based Model for Long-Range Reorderings in SMT , 2009, WMT@EACL.

[24]  Mauro Cettolo,et al.  WIT3: Web Inventory of Transcribed and Translated Talks , 2012, EAMT.

[25]  Jan Niehues,et al.  The IWSLT 2011 Evaluation Campaign on Automatic Talk Translation , 2012, LREC.

[26]  Matthew G. Snover,et al.  A Study of Translation Edit Rate with Targeted Human Annotation , 2006, AMTA.

[27]  José B. Mariño,et al.  System Combination for Machine Translation of Spoken and Written Language , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[28]  Hermann Ney,et al.  POS-based Word Reorderings for Statistical Machine Translation , 2006, LREC.

[29]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[30]  Jan Niehues,et al.  The KIT English-French translation systems for IWSLT 2011 , 2011, IWSLT.

[31]  Shankar Kumar,et al.  Minimum Bayes-Risk Decoding for Statistical Machine Translation , 2004, NAACL.

[32]  Hermann Ney,et al.  Jane: Open Source Hierarchical Translation, Extended with Reordering and Lexicon Models , 2010, WMT@ACL.

[33]  S. Vogel,et al.  SMT decoder dissected: word reordering , 2003, International Conference on Natural Language Processing and Knowledge Engineering, 2003. Proceedings. 2003.

[34]  Frankie James,et al.  Modified Kneser-Ney Smoothing of n-gram Models , 2000 .

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

[36]  S. Alexander,et al.  Seventh Framework Programme (FP7) , 2011 .

[37]  Giuseppe Riccardi,et al.  Computing consensus translation from multiple machine translation systems , 2001, IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01..

[38]  Sebastian Stüker,et al.  Overview of the IWSLT 2011 evaluation campaign , 2011, IWSLT.

[39]  Hermann Ney,et al.  Jane: an advanced freely available hierarchical machine translation toolkit , 2012, Machine Translation.

[40]  Christopher D. Manning,et al.  A Simple and Effective Hierarchical Phrase Reordering Model , 2008, EMNLP.

[41]  Hermann Ney,et al.  A Systematic Comparison of Various Statistical Alignment Models , 2003, CL.

[42]  William D. Lewis,et al.  Intelligent Selection of Language Model Training Data , 2010, ACL.

[43]  Jan Niehues,et al.  Continuous space language models using restricted Boltzmann machines , 2012, IWSLT.

[44]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[45]  Holger Schwenk,et al.  Large, Pruned or Continuous Space Language Models on a GPU for Statistical Machine Translation , 2012, WLM@NAACL-HLT.

[46]  Philipp Koehn,et al.  Explorer Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation , 2005 .

[47]  Arianna Bisazza,et al.  Fill-up versus interpolation methods for phrase-based SMT adaptation , 2011, IWSLT.

[48]  Andreas Eisele,et al.  MultiUN: A Multilingual Corpus from United Nation Documents , 2010, LREC.

[49]  A. Waibel,et al.  Detailed Analysis of Different Strategies for Phrase Table Adaptation in SMT , 2012, AMTA.

[50]  Christopher D. Manning,et al.  Parsing Three German Treebanks: Lexicalized and Unlexicalized Baselines , 2008 .

[51]  David Chiang,et al.  Forest Rescoring: Faster Decoding with Integrated Language Models , 2007, ACL.

[52]  Mauro Cettolo,et al.  IRSTLM: an open source toolkit for handling large scale language models , 2008, INTERSPEECH.

[53]  F. Béchet.  LIA―PHON: Un système complet de phonétisation de textes , 2001 .

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

[55]  Marcin Junczys-Dowmunt,et al.  Phrasal Rank-Encoding: Exploiting Phrase Redundancy and Translational Relations for Phrase Table Compression , 2012, Prague Bull. Math. Linguistics.

[56]  Nadir Durrani,et al.  Edinburgh’s Machine Translation Systems for European Language Pairs , 2013, WMT@ACL.

[57]  Li Deng,et al.  Maximum Expected BLEU Training of Phrase and Lexicon Translation Models , 2012, ACL.

[58]  Markus Freitag,et al.  Joint WMT 2013 Submission of the QUAERO Project , 2013, WMT@ACL.

[59]  Jan Niehues,et al.  Wider Context by Using Bilingual Language Models in Machine Translation , 2011, WMT@EMNLP.