Improved Word-Level System Combination for Machine Translation

Recently, confusion network decoding has been applied in machine translation system combination. Due to errors in the hypothesis alignment, decoding may result in ungrammatical combination outputs. This paper describes an improved confusion network based method to combine outputs from multiple MT systems. In this approach, arbitrary features may be added log-linearly into the objective function, thus allowing language model expansion and re-scoring. Also, a novel method to automatically select the hypothesis which other hypotheses are aligned against is proposed. A generic weight tuning algorithm may be used to optimize various automatic evaluation metrics including TER, BLEU and METEOR. The experiments using the 2005 Arabic to English and Chinese to English NIST MT evaluation tasks show significant improvements in BLEU scores compared to earlier confusion network decoding based methods.

[1]  D. Anderson,et al.  Algorithms for minimization without derivatives , 1974 .

[2]  Mari Ostendorf,et al.  Integration of Diverse Recognition Methodologies Through Reevaluation of N-Best Sentence Hypotheses , 1991, HLT.

[3]  Sergei Nirenburg,et al.  Three Heads are Better than One , 1994, ANLP.

[4]  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.

[5]  Andreas Stolcke,et al.  Finding consensus in speech recognition: word error minimization and other applications of confusion networks , 2000, Comput. Speech Lang..

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

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

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

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

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

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

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

[13]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

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

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

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

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

[18]  Daniel Marcu,et al.  Scalable Inference and Training of Context-Rich Syntactic Translation Models , 2006, ACL.

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

[20]  Hichem Sahbi,et al.  Consensus Network Decoding for Statistical Machine Translation System Combination , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.