Improved Semantic Parsers For If-Then Statements

Digital personal assistants are becoming both more common and more useful. The major NLP challenge for personal assistants is machine understanding: translating natural language user commands into an executable representation. This paper focuses on understanding rules written as If-Then statements, though the techniques should be portable to other semantic parsing tasks. We view understanding as structure prediction and show improved models using both conventional techniques and neural network models. We also discuss various ways to improve generalization and reduce overfitting: synthetic training data from paraphrase, grammar combinations, feature selection and ensembles of multiple systems. An ensemble of these techniques achieves a new state of the art result with 8% accuracy improvement.

[1]  Jay Earley,et al.  An efficient context-free parsing algorithm , 1970, Commun. ACM.

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

[3]  Adwait Ratnaparkhi,et al.  Learning to Parse Natural Language with Maximum Entropy Models , 1999, Machine Learning.

[4]  Percy Liang,et al.  Semi-Supervised Learning for Natural Language , 2005 .

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

[6]  Rohit J. Kate,et al.  Learning to Transform Natural to Formal Languages , 2005, AAAI.

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

[8]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[9]  Luke S. Zettlemoyer,et al.  Reinforcement Learning for Mapping Instructions to Actions , 2009, ACL.

[10]  Bernd Bohnet,et al.  Top Accuracy and Fast Dependency Parsing is not a Contradiction , 2010, COLING.

[11]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[12]  David L. Chen.  Fast Online Lexicon Learning for Grounded Language Acquisition , 2012, ACL.

[13]  Jacob Andreas,et al.  Semantic Parsing as Machine Translation , 2013, ACL.

[14]  Andrew Chou,et al.  Semantic Parsing on Freebase from Question-Answer Pairs , 2013, EMNLP.

[15]  Gregory Shakhnarovich,et al.  A Systematic Exploration of Diversity in Machine Translation , 2013, EMNLP.

[16]  Chris Callison-Burch,et al.  PPDB: The Paraphrase Database , 2013, NAACL.

[17]  Richard M. Schwartz,et al.  Fast and Robust Neural Network Joint Models for Statistical Machine Translation , 2014, ACL.

[18]  Nando de Freitas,et al.  A Deep Architecture for Semantic Parsing , 2014, ACL 2014.

[19]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[20]  Sumit Gulwani,et al.  NLyze: interactive programming by natural language for spreadsheet data analysis and manipulation , 2014, SIGMOD Conference.

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

[22]  Harm de Vries,et al.  RMSProp and equilibrated adaptive learning rates for non-convex optimization. , 2015 .

[23]  Geoffrey E. Hinton,et al.  Grammar as a Foreign Language , 2014, NIPS.

[24]  Noah A. Smith,et al.  Improved Transition-based Parsing by Modeling Characters instead of Words with LSTMs , 2015, EMNLP.

[25]  Luke S. Zettlemoyer,et al.  Broad-coverage CCG Semantic Parsing with AMR , 2015, EMNLP.

[26]  Raymond J. Mooney,et al.  Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes , 2015, ACL.

[27]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

[28]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[29]  Zhengdong Lu,et al.  Neural Enquirer: Learning to Query Tables in Natural Language , 2016, IEEE Data Eng. Bull..

[30]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).