A Probabilistic Forest-to-String Model for Language Generation from Typed Lambda Calculus Expressions

This paper describes a novel probabilistic approach for generating natural language sentences from their underlying semantics in the form of typed lambda calculus. The approach is built on top of a novel reduction-based weighted synchronous context free grammar formalism, which facilitates the transformation process from typed lambda calculus into natural language sentences. Sentences can then be generated based on such grammar rules with a log-linear model. To acquire such grammar rules automatically in an unsupervised manner, we also propose a novel approach with a generative model, which maps from sub-expressions of logical forms to word sequences in natural language sentences. Experiments on benchmark datasets for both English and Chinese generation tasks yield significant improvements over results obtained by two state-of-the-art machine translation models, in terms of both automatic metrics and human evaluation.

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

[2]  Chris Callison-Burch,et al.  Demonstration of Joshua: An Open Source Toolkit for Parsing-based Machine Translation , 2009, ACL.

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

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

[5]  Gérard P. Huet,et al.  A Unification Algorithm for Typed lambda-Calculus , 1975, Theor. Comput. Sci..

[6]  Henk Barendregt,et al.  The Lambda Calculus: Its Syntax and Semantics , 1985 .

[7]  Luke S. Zettlemoyer,et al.  Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars , 2005, UAI.

[8]  Christopher D. Manning,et al.  Accurate Non-Hierarchical Phrase-Based Translation , 2010, NAACL.

[9]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[10]  Hwee Tou Ng,et al.  Natural Language Generation with Tree Conditional Random Fields , 2009, EMNLP.

[11]  Raymond J. Mooney,et al.  Learning to sportscast: a test of grounded language acquisition , 2008, ICML '08.

[12]  George R. Doddington,et al.  Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics , 2002 .

[13]  Mark Steedman,et al.  Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification , 2010, EMNLP.

[14]  Ben Taskar,et al.  Alignment by Agreement , 2006, NAACL.

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

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

[17]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[18]  Rohit J. Kate,et al.  Using String-Kernels for Learning Semantic Parsers , 2006, ACL.

[19]  Hwee Tou Ng,et al.  A Generative Model for Parsing Natural Language to Meaning Representations , 2008, EMNLP.

[20]  Raymond J. Mooney,et al.  Generation by Inverting a Semantic Parser that Uses Statistical Machine Translation , 2007, NAACL.

[21]  J. Baker.  Trainable grammars for speech recognition , 1979 .

[22]  Luke S. Zettlemoyer,et al.  Learning Context-Dependent Mappings from Sentences to Logical Form , 2009, ACL.

[23]  Luke S. Zettlemoyer,et al.  Online Learning of Relaxed CCG Grammars for Parsing to Logical Form , 2007, EMNLP.

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

[25]  Irene Langkilde-Geary,et al.  Forest-Based Statistical Sentence Generation , 2000, ANLP.

[26]  Hadar Shemtov,et al.  Generation of Paraphrases from Ambiguous Logical Forms , 1996, COLING.

[27]  Omar Zaidan,et al.  Z-MERT: A Fully Configurable Open Source Tool for Minimum Error Rate Training of Machine Translation Systems , 2009, Prague Bull. Math. Linguistics.

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

[29]  Alfred V. Aho,et al.  Syntax Directed Translations and the Pushdown Assembler , 1969, J. Comput. Syst. Sci..

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

[31]  Raymond J. Mooney,et al.  Learning a Compositional Semantic Parser using an Existing Syntactic Parser , 2009, ACL.

[32]  F ChenStanley,et al.  An Empirical Study of Smoothing Techniques for Language Modeling , 1996, ACL.

[33]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[34]  GERARD P. HUET,et al.  The Undecidability of Unification in Third Order Logic , 1973, Inf. Control..

[35]  Dan Klein,et al.  A Simple Domain-Independent Probabilistic Approach to Generation , 2010, EMNLP.

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

[37]  Hermann Ney,et al.  The Alignment Template Approach to Statistical Machine Translation , 2004, CL.

[38]  Raymond J. Mooney,et al.  Learning for Semantic Parsing with Statistical Machine Translation , 2006, NAACL.

[39]  Juen-tin Wang,et al.  On Computational Sentence Generation From Logical Form , 1980, COLING.

[40]  Gertjan van Noord,et al.  Semantic-Head-Driven Generation , 1990, Comput. Linguistics.

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

[42]  Gregory Kuhlmann and Peter Stone and Raymond J. Mooney and Shavlik.  Guiding a Reinforcement Learner with Natural Language Advice: Initial Results in RoboCup Soccer , 2004, AAAI 2004.

[43]  Raymond J. Mooney,et al.  Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus , 2007, ACL.