The RWTH System Combination System for WMT 2010

RWTH participated in the System Combination task of the Sixth Workshop on Statistical Machine Translation (WMT 2011). For three language pairs, we combined 6 to 14 systems into a single consensus translation. A three-level meta-combination scheme combining six different system combination setups with three different engines was applied on the French--English language pair. Depending on the language pair, improvements versus the best single system are in the range of +1.9% and +2.5% abs. on BLEU, and between −1.8% and −2.4% abs. on TER. Novel techniques compared with RWTH's submission to WMT 2010 include two additional system combination engines, an additional word alignment technique, meta combination, and additional optimization techniques.

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

[2]  Hermann Ney,et al.  HMM-Based Word Alignment in Statistical Translation , 1996, COLING.

[3]  Jonathan G. Fiscus,et al.  A post-processing system to yield reduced word error rates: Recognizer Output Voting Error Reduction (ROVER) , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

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

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

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

[7]  Hermann Ney,et al.  Symmetric Word Alignments for Statistical Machine Translation , 2004, COLING.

[8]  Chin-Yew Lin,et al.  ORANGE: a Method for Evaluating Automatic Evaluation Metrics for Machine Translation , 2004, COLING.

[9]  Alon Lavie,et al.  Multi-engine machine translation guided by explicit word matching , 2005, EAMT.

[10]  Frank Vanden Berghen,et al.  CONDOR, a new parallel, constrained extension of Powell's UOBYQA algorithm: experimental results and comparison with the DFO algorithm , 2005 .

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

[12]  Hermann Ney,et al.  Computing Consensus Translation for Multiple Machine Translation Systems Using Enhanced Hypothesis Alignment , 2006, EACL.

[13]  Hermann Ney,et al.  N-Gram Posterior Probabilities for Statistical Machine Translation , 2006, WMT@HLT-NAACL.

[14]  Richard M. Schwartz,et al.  Improved Word-Level System Combination for Machine Translation , 2007, ACL.

[15]  Johan Schalkwyk,et al.  OpenFst: A General and Efficient Weighted Finite-State Transducer Library , 2007, CIAA.

[16]  Hermann Ney,et al.  iROVER: Improving System Combination with Classification , 2007, NAACL.

[17]  Richard M. Schwartz,et al.  Combining Outputs from Multiple Machine Translation Systems , 2007, NAACL.

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

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

[20]  Hermann Ney,et al.  Triplet Lexicon Models for Statistical Machine Translation , 2008, EMNLP.

[21]  Jianfeng Gao,et al.  Indirect-HMM-based Hypothesis Alignment for Combining Outputs from Machine Translation Systems , 2008, EMNLP.

[22]  Hermann Ney,et al.  Automatic Evaluation Measures for Statistical Machine Translation System Optimization , 2008, LREC.

[23]  H. Ney,et al.  The RWTH System Combination System for WMT 2011 , 2009, WMT@EACL.

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