Induction of Probabilistic Synchronous Tree-Insertion Grammars for Machine Translation

The more expressive and flexible a base formalism for machine translation is, the less efficient parsing of it will be. However, even among formalisms with the same parse complexity, some formalisms better realize the desired characteristics for machine translation formalisms than others. We introduce a particular formalism, probabilistic synchronous treeinsertion grammar (PSTIG) that we argue satisfies the desiderata optimally within the class of formalisms that can be parsed no less efficiently than context-free grammars and demonstrate that it outperforms state-of-the-art word-based and phrasebased finite-state translation models on training and test data taken from the EuroParl corpus (Koehn, 2005). We then argue that a higher level of translation quality can be achieved by hybridizing our induced model with elementary structures produced using supervised techniques such as those of Groves et al. (2004).

[1]  Steve Young,et al.  Applications of stochastic context-free grammars using the Inside-Outside algorithm , 1990 .

[2]  Yuan Ding,et al.  Machine Translation Using Probabilistic Synchronous Dependency Insertion Grammars , 2005, ACL.

[3]  Richard C. Waters,et al.  Stochastic Lexicalized Context-Free Grammar , 1993, IWPT.

[4]  Andy Way,et al.  Robust Sub-Sentential Alignment of Phrase-Structure Trees , 2004, COLING.

[5]  Andy Way,et al.  Hybrid Example-Based SMT: the Best of Both Worlds? , 2005, ParallelText@ACL.

[6]  Daniel Marcu,et al.  A Phrase-Based,Joint Probability Model for Statistical Machine Translation , 2002, EMNLP.

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

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

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

[10]  Stuart M. Shieber,et al.  Principles and Implementation of Deductive Parsing , 1994, J. Log. Program..

[11]  I. Dan Melamed,et al.  Statistical Machine Translation by Parsing , 2004, ACL.

[12]  I. Dan Melamed,et al.  Multitext Grammars and Synchronous Parsers , 2003, NAACL.

[13]  STUART M. SHIEBER.  RESTRICTING THE WEAK‐GENERATIVE CAPACITY OF SYNCHRONOUS TREE‐ADJOINING GRAMMARS , 1994, Comput. Intell..

[14]  Michael Collins,et al.  Discriminative Reranking for Natural Language Parsing , 2000, CL.

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

[16]  Rebecca Hwa,et al.  Learning probabilistic lexicalized grammars for natural language processing , 2001 .

[17]  Aravind K. Joshi,et al.  Parsing Strategies with ‘Lexicalized’ Grammars: Application to Tree Adjoining Grammars , 1988, COLING.

[18]  Richard C. Waters,et al.  Tree Insertion Grammar: A Cubic-Time, Parsable Formalism that Lexicalizes Context-Free Grammar without Changing the Trees Produced , 1995, CL.

[19]  Daniel Marcu,et al.  Statistical Phrase-Based Translation , 2003, NAACL.

[20]  Kevin Knight,et al.  A Decoder for Syntax-based Statistical MT , 2002, ACL.

[21]  Alexander M. Rush,et al.  Induction of Probabilistic Synchronous Tree-Insertion Grammars , 2005 .

[22]  Giorgio Satta,et al.  Generalized Multitext Grammars , 2004, ACL.

[23]  Richard C. Waters,et al.  Lexicalized Context-Free Grammars , 1993, ACL.

[24]  Giorgio Satta,et al.  Efficient Parsing for Bilexical Context-Free Grammars and Head Automaton Grammars , 1999, ACL.

[25]  Joshua Goodman,et al.  Semiring Parsing , 1999, CL.

[26]  Stuart M. Shieber,et al.  Synchronous Tree-Adjoining Grammars , 1990, COLING.

[27]  Mary Hearne,et al.  Final Report of the 2005 Language Engineering Workshop on Statistical Machine Translation by Parsing , 2005 .