Neural sentence generation from formal semantics

Sequence-to-sequence models have shown strong performance in a wide range of NLP tasks, yet their applications to sentence generation from logical representations are underdeveloped. In this paper, we present a sequence-to-sequence model for generating sentences from logical meaning representations based on event semantics. We use a semantic parsing system based on Combinatory Categorial Grammar (CCG) to obtain data annotated with logical formulas. We augment our sequence-to-sequence model with masking for predicates to constrain output sentences. We also propose a novel evaluation method for generation using Recognizing Textual Entailment (RTE). Combining parsing and generation, we test whether or not the output sentence entails the original text and vice versa. Experiments showed that our model outperformed a baseline with respect to both BLEU scores and accuracies in RTE.

[1]  Christopher Potts,et al.  A large annotated corpus for learning natural language inference , 2015, EMNLP.

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

[3]  Michael White,et al.  Efficient Realization of Coordinate Structures in Combinatory Categorial Grammar , 2006 .

[4]  Yuji Matsumoto,et al.  A* CCG Parsing with a Supertag and Dependency Factored Model , 2019 .

[5]  Pascual Martínez-Gómez,et al.  On-demand Injection of Lexical Knowledge for Recognising Textual Entailment , 2017, EACL.

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

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

[8]  Anna Freud,et al.  Grammatical Framework Programming With Multilingual Grammars , 2016 .

[9]  Mark Steedman,et al.  A* CCG Parsing with a Supertag-factored Model , 2014, EMNLP.

[10]  Marco Marelli,et al.  A SICK cure for the evaluation of compositional distributional semantic models , 2014, LREC.

[11]  Martin Kay,et al.  Chart Generation , 1996, ACL.

[12]  Shashi Narayan,et al.  Split and Rephrase , 2017, EMNLP.

[13]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[14]  Yoav Goldberg,et al.  Split and Rephrase: Better Evaluation and a Stronger Baseline , 2018, ACL.

[15]  Daniel Jurafsky,et al.  Robust Machine Translation Evaluation with Entailment Features , 2009, ACL.

[16]  Pascual Martínez-Gómez,et al.  Determining Semantic Textual Similarity using Natural Deduction Proofs , 2017, EMNLP.

[17]  Pascual Martínez-Gómez,et al.  Higher-order logical inference with compositional semantics , 2015, EMNLP.

[18]  Johan Bos,et al.  Open-Domain Semantic Parsing with Boxer , 2015, NODALIDA.

[19]  Alastair Butler.  Deterministic natural language generation from meaning representations for machine translation , 2016, SedMT@NAACL-HLT.

[20]  Terence Parsons,et al.  Events in the Semantics of English: A Study in Subatomic Semantics , 1990 .

[21]  Johan Bos,et al.  Wide-Coverage Semantic Analysis with Boxer , 2008, STEP.

[22]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[23]  Mark Steedman,et al.  The syntactic process , 2004, Language, speech, and communication.

[24]  Jian Wang,et al.  Premise Selection for Theorem Proving by Deep Graph Embedding , 2017, NIPS.

[25]  Mark Steedman,et al.  Taking Scope - The Natural Semantics of Quantifiers , 2011 .

[26]  Raymond J. Mooney,et al.  Learning to Parse Database Queries Using Inductive Logic Programming , 1996, AAAI/IAAI, Vol. 2.

[27]  James R. Curran,et al.  Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models , 2007, Computational Linguistics.

[28]  Yejin Choi,et al.  Neural AMR: Sequence-to-Sequence Models for Parsing and Generation , 2017, ACL.

[29]  Omer Levy,et al.  Modeling Extractive Sentence Intersection via Subtree Entailment , 2016, COLING.

[30]  Lasha Abzianidze,et al.  A Tableau Prover for Natural Logic and Language , 2015, EMNLP.

[31]  Matthew R. Walter,et al.  What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment , 2015, NAACL.

[32]  Stephan Oepen,et al.  High Efficiency Realization for a Wide-Coverage Unification Grammar , 2005, IJCNLP.

[33]  Johan Bos,et al.  Squib: Expressive Power of Abstract Meaning Representations , 2016, CL.

[34]  Pascual Martínez-Gómez,et al.  ccg2lambda: A Compositional Semantics System , 2016, ACL.

[35]  John Carroll,et al.  An Efficient Chart Generator for (Semi-)Lexicalist Grammars , 2001 .

[36]  Michael White,et al.  Perceptron Reranking for CCG Realization , 2009, EMNLP.