Referential semantic language modeling for data-poor domains

This paper describes a referential semantic language model that achieves accurate recognition in user-defined domains with no available domain-specific training corpora. This model is interesting in that, unlike similar recent systems, it exploits context dynamically, using incremental processing and limited stack memory of an HMM-like time series model to constrain search.

[1]  Nicholas Haddock,et al.  Computational models of incremental semantic interpretation , 1989 .

[2]  Anthony J. Robinson,et al.  An application of recurrent nets to phone probability estimation , 1994, IEEE Trans. Neural Networks.

[3]  Ellen Campana,et al.  Incremental understanding in human-computer dialogue and experimental evidence for advantages over nonincremental methods , 2007 .

[4]  Jerry R. Hobbs.  Ontological Promiscuity , 1985, ACL.

[5]  C. S. Mellish.  Computer interpretation of natural language descriptions , 2000 .

[6]  Oliver Lemon,et al.  multithreaded context for robust conversational interfaces: Context-sensitive speech recognition and interpretation of corrective fragments , 2004, TCHI.

[7]  Ronald J. Brachman,et al.  An overview of the KL-ONE Knowledge Representation System , 1985 .

[8]  David DeVault,et al.  Domain Inference in Incremental Interpretation , 2003 .

[9]  Deb Roy,et al.  Grounded Semantic Composition for Visual Scenes , 2011, J. Artif. Intell. Res..

[10]  William Schuler,et al.  Computational Properties of Environment-based Disambiguation , 2001, ACL.

[11]  J. Baker,et al.  The DRAGON system--An overview , 1975 .

[12]  Alonzo Church,et al.  A formulation of the simple theory of types , 1940, Journal of Symbolic Logic.

[13]  Stephanie Seneff,et al.  A dynamic vocabulary spoken dialogue interface , 2004, INTERSPEECH.

[14]  Kevin P. Murphy,et al.  Linear-time inference in Hierarchical HMMs , 2001, NIPS.

[15]  W. Fisher,et al.  An acoustic‐phonetic data base , 1987 .

[16]  Lalit R. Bahl,et al.  Design of a linguistic statistical decoder for the recognition of continuous speech , 1975, IEEE Trans. Inf. Theory.