A Joint Dependency Model of Morphological and Syntactic Structure for Statistical Machine Translation

When translating between two languages that differ in their degree of morphological synthesis, syntactic structures in one language may be realized as morphological structures in the other, and SMT models need a mechanism to learn such translations. Prior work has used morpheme splitting with flat representations that do not encode the hierarchical structure between morphemes, but this structure is relevant for learning morphosyntactic constraints and selectional preferences. We propose to model syntactic and morphological structure jointly in a dependency translation model, allowing the system to generalize to the level of morphemes. We present a dependency representation of German compounds and particle verbs that results in improvements in translation quality of 1.4‐1.8 BLEU in the WMT English‐German translation task.

[1]  Hermann Ney,et al.  Improving SMT quality with morpho-syntactic analysis , 2000, COLING.

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

[3]  Ulrich Heid,et al.  SMOR: A German Computational Morphology Covering Derivation, Composition and Inflection , 2004, LREC.

[4]  Hermann Ney,et al.  Statistical Machine Translation of German Compound Words , 2006, FinTAL.

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

[6]  Kilian A. Foth.  Eine umfassende Constraint-Dependenz-Grammatik des Deutschen , 2006 .

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

[8]  Daniel Marcu,et al.  Binarizing Syntax Trees to Improve Syntax-Based Machine Translation Accuracy , 2007, EMNLP.

[9]  Jinxi Xu,et al.  String-to-Dependency Statistical Machine Translation , 2010, CL.

[10]  Alexander M. Fraser,et al.  How to Avoid Burning Ducks: Combining Linguistic Analysis and Corpus Statistics for German Compound Processing , 2010, WMT@ACL.

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

[12]  Andrew M. Dai,et al.  Language-independent compound splitting with morphological operations , 2011, ACL.

[13]  Alexander M. Fraser,et al.  Modeling Inflection and Word-Formation in SMT , 2012, EACL.

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

[15]  Ashish Vaswani,et al.  Decoding with Large-Scale Neural Language Models Improves Translation , 2013, EMNLP.

[16]  Gerold Schneider,et al.  Exploiting Synergies Between Open Resources for German Dependency Parsing, POS-tagging, and Morphological Analysis , 2013, RANLP.

[17]  Alexander M. Fraser,et al.  Distinguishing Degrees of Compositionality in Compound Splitting for Statistical Machine Translation , 2014 .

[18]  Philipp Koehn,et al.  Edinburgh's Syntax-Based Systems at WMT 2014 , 2014, WMT@ACL.

[19]  Rico Sennrich,et al.  Zmorge: A German Morphological Lexicon Extracted from Wiktionary , 2014, LREC.

[20]  Philipp Koehn,et al.  Preference Grammars and Soft Syntactic Constraints for GHKM Syntax-based Statistical Machine Translation , 2014, SSST@EMNLP.

[21]  Philipp Koehn,et al.  Edinburgh’s Syntax-Based Systems at WMT 2014 , 2014 .

[22]  Rico Sennrich,et al.  Modelling and Optimizing on Syntactic N-Grams for Statistical Machine Translation , 2015, TACL.

[23]  Yoshua Bengio,et al.  Montreal Neural Machine Translation Systems for WMT’15 , 2015, WMT@EMNLP.