Matching utterances to rich knowledge structures to acquire a model of the speaker's goal

An ultimate goal of AI is to build end-to-end systems that interpret natural language, reason over the resulting logical forms, and perform actions based on that reasoning. This requires systems from separate fields be brought together, but often this exposes representational gaps between them. The logical forms from a language interpreter may mirror the surface forms of utterances too closely to be usable as-is, given a reasoner's requirements for knowledge representations. What is needed is a system that can match logical forms to background knowledge flexibly to acquire a rich semantic model of the speaker's goal. In this paper, we present such a "matcher" that uses semantic transformations to overcome structural differences between the two representations. We evaluate this matcher in a MUC-like template-filling task and compare its performance to that of two similar systems.

[1]  John F. Sowa,et al.  Conceptual Structures: Information Processing in Mind and Machine , 1983 .

[2]  Nancy Chinchor,et al.  MUC-3 evaluation metrics , 1991, MUC.

[3]  Jan Alexandersson,et al.  Overlay as the Basic Operation for Discourse Processing in a Multimodal Dialogue System , 2001 .

[4]  Nancy Chinchor,et al.  Overview of MUC-7 , 1998, MUC.

[5]  Peter Yeh and Bruce Porter and Ken Barker,et al.  Mining Transformation Rules for Semantic Matching , 2004 .

[6]  Nicola Guarino,et al.  OntoSeek: content-based access to the Web , 1999, IEEE Intell. Syst..

[7]  Ken Barker,et al.  Transformation rules for knowledge-based pattern matching , 2003 .

[8]  Yorick Wilks,et al.  University of Sheffield: description of the LaSIE system as used for MUC-6 , 1995, MUC.

[9]  Robert Gaizauskas,et al.  Quantitative evaluation of coreference algorithms in an information extraction system , 2000 .

[10]  Yong Yu,et al.  Conceptual Graph Matching for Semantic Search , 2002, ICCS.

[11]  Peter Z. Yeh,et al.  Using transformations to improve semantic matching , 2003, K-CAP '03.

[12]  Yorick Wilks,et al.  University of Sheffield: Description of the LaSIE System as Used for MUC-6 , 1995, MUC.

[13]  Peter Clark,et al.  A library of generic concepts for composing knowledge bases , 2001, K-CAP '01.

[14]  Philippe Mulhem,et al.  Fuzzy Conceptual Graphs for Matching Images of Natural Scenes , 2001, IJCAI.

[15]  Philipp Cimiano,et al.  Ontology-Driven Discourse Analysis in GenIE , 2003, NLDB.

[16]  Ramanathan V. Guha,et al.  Building Large Knowledge-Based Systems: Representation and Inference in the Cyc Project , 1990 .

[17]  Ramanathan V. Guha,et al.  Building large knowledge-based systems , 1989 .

[18]  Michel Chein,et al.  An Experiment in Document Retrieval Using Conceptual Graphs , 1997, ICCS.

[19]  Norman Y. Foo,et al.  Semantic distance in conceptual graphs , 1992 .