The HDU Discriminative SMT System for Constrained Data PatentMT at NTCIR10

We describe the statistical machine translation (SMT) systems developed at Heidelberg University for the Chinese-toEnglish and Japanese-to-English PatentMT subtasks at the NTCIR10 workshop. The core system used in both subtasks is a combination of hierarchical phrase-based translation and discriminative training using either large feature sets and ‘1=‘2 regularization (for Japanese-to-English) or variants of soft syntactic constraints (for Chinese-to-English). Our goal is to address the twofold nature of patents by exploiting the repetitive nature of patents through feature sharing in a multi-task learning setup (used in the Japaneseto-English translation subtask), and by countersteering complex word order dierences with syntactic features (used in

[1]  Stefan Riezler,et al.  Analyzing Parallelism and Domain Similarities in the MAREC Patent Corpus , 2012, IRFC.

[2]  S. T. Buckland,et al.  Computer-Intensive Methods for Testing Hypotheses. , 1990 .

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

[4]  Eiichiro Sumita,et al.  Overview of the Patent Machine Translation Task at the NTCIR-10 Workshop , 2011, NTCIR.

[5]  Phil Blunsom,et al.  Probabilistic Inference for Machine Translation , 2008, EMNLP.

[6]  Philip Resnik,et al.  Soft Syntactic Constraints for Hierarchical Phrased-Based Translation , 2008, ACL.

[7]  Hermann Ney,et al.  Analysing soft syntax features and heuristics for hierarchical phrase based machine translation. , 2008, IWSLT.

[8]  Alon Lavie,et al.  Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability , 2011, ACL.

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

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

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

[12]  Adam Lopez,et al.  Hierarchical Phrase-Based Translation with Suffix Arrays , 2007, EMNLP.

[13]  Shankar Kumar,et al.  Efficient Minimum Error Rate Training and Minimum Bayes-Risk Decoding for Translation Hypergraphs and Lattices , 2009, ACL/IJCNLP.

[14]  Mark Hopkins,et al.  Tuning as Ranking , 2011, EMNLP.

[15]  Anoop Sarkar,et al.  Discriminative Reranking for Machine Translation , 2004, NAACL.

[16]  Taro Watanabe,et al.  NTT statistical machine translation for IWSLT 2006 , 2006, IWSLT.

[17]  Markus Freitag,et al.  The RWTH Aachen System for NTCIR-10 PatentMT , 2013, NTCIR.

[18]  Stefan Riezler,et al.  On Some Pitfalls in Automatic Evaluation and Significance Testing for MT , 2005, IEEvaluation@ACL.

[19]  David Chiang,et al.  Hierarchical Phrase-Based Translation , 2007, CL.

[20]  Chris Dyer,et al.  Joint Feature Selection in Distributed Stochastic Learning for Large-Scale Discriminative Training in SMT , 2012, ACL.

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

[22]  K. J. Evans,et al.  Computer Intensive Methods for Testing Hypotheses: An Introduction , 1990 .

[23]  Spyridon Matsoukas,et al.  BBN's Systems for the Chinese-English Sub-task of the NTCIR-10 PatentMT Evaluation , 2013, NTCIR.