Learning a semantic parser from spoken utterances

Semantic parsers map natural language input into semantic representations. In this paper, we present an approach that learns a semantic parser in the form of a lexicon and an inventory of syntactic patterns from ambiguous training data which is applicable to spoken utterances. We only assume the availability of a task-independent phoneme recognizer, making it easy to adapt to other tasks and yielding no a priori restriction concerning the vocabulary that the parser can process. In spite of these low requirements, we show that our approach can be successfully applied to both spoken and written data.

[1]  Philipp Cimiano,et al.  A usage-based model for the online induction of constructions from phoneme sequences , 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

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

[3]  Marc Schröder,et al.  The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching , 2003, Int. J. Speech Technol..

[4]  Elmar Nöth,et al.  Using EM-trained string-edit distances for approximate matching of acoustic morphemes , 2002, INTERSPEECH.

[5]  A. Goldberg,et al.  Construction grammar. , 2010, Wiley interdisciplinary reviews. Cognitive science.

[6]  Christophe Cerisara,et al.  Automatic discovery of topics and acoustic morphemes from speech , 2009, Comput. Speech Lang..

[7]  Chen Yu,et al.  The Role of Embodied Intention in Early Lexical Acquisition , 2005, Cogn. Sci..

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

[9]  Takashi Nose,et al.  Learning lexicons from spoken utterances based on statistical model selection , 2009, INTERSPEECH.

[10]  Afsaneh Fazly,et al.  A Probabilistic Computational Model of Cross-Situational Word Learning , 2010, Cogn. Sci..

[11]  Philipp Cimiano,et al.  A Computational Model for the Item-Based Induction of Construction Networks , 2014, Cogn. Sci..

[12]  Philipp Cimiano,et al.  An unsupervised algorithm for the induction of constructions , 2011, 2011 IEEE International Conference on Development and Learning (ICDL).

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

[14]  Mark Johnson,et al.  Reducing Grounded Learning Tasks To Grammatical Inference , 2011, EMNLP.

[15]  Alex Pentland,et al.  Learning words from sights and sounds: a computational model , 2002, Cogn. Sci..

[16]  Dana H. Ballard,et al.  A Computational Model of Embodied Language Learning , 2003 .

[17]  Raymond J. Mooney,et al.  Training a Multilingual Sportscaster: Using Perceptual Context to Learn Language , 2014, J. Artif. Intell. Res..

[18]  Richard M. Stern,et al.  The 1996 Hub-4 Sphinx-3 System , 1997 .