ABSTRACT
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.
- J. Alexandersson and T. Becker. Overlay as the basic operation for discourse processing in a multimodal dialogue system. In IJCAI Workshop on Knowledge and Reasoning in Practical Dialogue Systems, 2001.Google Scholar
- J. Alexandersson and T. Becker. The formal foundations underlying overlay. In IWCS-5, 2003.Google Scholar
- K. Barker, B. Porter, and P. Clark. A library of generic concepts for composing knowledge bases. In KCAP, 2001. Google ScholarDigital Library
- N. Chinchor. MUC-3 evaluation metrics. In MUC-3, 1991. Google ScholarDigital Library
- N. Chinchor. Overview of MUC-7/MET-2. In MUC-7, 1998.Google Scholar
- P. Cimiano. Ontology-driven discourse analysis in GenIE. In NLDB, 2003.Google Scholar
- N. Foo, B. Garner, A. Rao, and E. Tsui. Semantic distance in conceptual graphs. In P. Eklund, T. Nagle, J. Nagle, L. Gerhotz, and E. Horwood, editors, Current Directions in Conceptual Structure Research, 1992. Google ScholarDigital Library
- R. Gaizauskas and K. Humphreys. Quantitative evaluation of coreference algorithms in an information extraction system. In S. Botley and T. McEnery, editors, Corpus-based and Computational Approaches to Discourse Anaphora, 1996.Google Scholar
- R. Gaizauskas, T. Wakao, K. Humphreys, H. Cunningham, and Y. Wilks. University of Sheffield: Description of the LaSIE system as used for MUC-6. In MUC-6, 1995. Google ScholarDigital Library
- D. Genest and M. Chein. An experiment in document retrieval using conceptual graphs. In ICCS, 1997. Google ScholarDigital Library
- N. Guarino, C. Masolo, and G. Vetere. Ontoseek: Content-based access to the web. IEEE Intelligent Systems, 14(3), 1999. Google ScholarDigital Library
- J. Hobbs, M. Stickel, P. Martin, and D. Edwards. Interpretation as abduction. In ACL, 1988. Google ScholarDigital Library
- K. Humphreys, R. Gaizauskas, S. Azzam, C. Huyck, B. Mitchell, H. Cunningham, and Y. Wilks. University of Sheffield: Description of the LaSIE-II system as used for MUC-7. In MUC-7, 1998.Google Scholar
- D. B. Lenat and R. Guha. Building Large Knowledge-Based Systems. Addison-Wesley, 1990. Google ScholarDigital Library
- P. Mulhem, W. Leow, and Y. Lee. Fuzzy conceptual graphs for matching images of natural scenes. In IJCAI, 2001. Google ScholarDigital Library
- J. F. Sowa. Conceptual Structures: Information Processing in Mind and Machine. Addison-Wesley, 1984. Google ScholarDigital Library
- P. Yeh, B. Porter, and K. Barker. Transformation rules for knowledge-based pattern matching. Technical Report UT-AI-TR-03-299, U.T. Austin, 2003.Google Scholar
- P. Yeh, B. Porter, and K. Barker. Using transformations to improve semantic matching. In KCAP, 2003. Google ScholarDigital Library
- P. Yeh, B. Porter, and K. Barker. Mining transformation rules for semantic matching. In ECML/PKDD 2nd International Workshop on Mining Graphs, Trees, and Sequences, 2004. Google ScholarDigital Library
- J. Zhong, H. Zhu, J. Li, and Y. Yu. Conceptual graph matching for semantic search. In ICCS, 2002. Google ScholarDigital Library
Index Terms
Matching utterances to rich knowledge structures to acquire a model of the speaker's goal
Recommendations
Knowledge acquisition for knowledge-based engineering systems
This paper is essentially concerned with the development of formal representations of knowledge required prior to the development of knowledge-based engineering systems (KBESs). Initially, the paper provides a brief introduction to knowledge-based ...
A knowledge based approach for capturing rich semantic representations from text for intelligent systems
In this paper, we present a knowledge based approach to capture semantic representations from text for intelligent systems that know the representations of interest in advance. Our approach performs this task by generating phrases from these ...
Using transformations to improve semantic matching
K-CAP '03: Proceedings of the 2nd international conference on Knowledge captureMany AI tasks require determining whether two knowledge representations encode the same knowledge. Solving this matching problem is hard because representations may encode the same content but differ substantially in form. Previous approaches to this ...
Comments