Abstract
Controlled and restricted dialogue systems are reliable enough to be deployed in various real world applications. The more conversational a dialogue system becomes, the more difficult and unreliable become recognition and processing. Numerous research projects are struggling to overcome the problems arising with more- or truly conversational dialogue system. We introduce a set of contextual coherence measurements that can improve the reliability of spoken dialogue systems, by including contextual knowledge at various stages in the natural language processing pipeline. We show that, situational knowledge can be successfully employed to resolve pragmatic ambiguities and that it can be coupled with ontological knowledge to resolve semantic ambiguities and to choose among competing automatic speech recognition hypotheses.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Allen, James and Georga Ferguson and Amanda Stent: An architecture for more realistic conversational system. In Proc. of Intelligent User Interfaces. (2001) 1–8
Allen, James: Natural Language Understanding. Ben. Cummings (1987)
Barr-Hillel, Y.: Logical Syntax and Semantics. Language, 20 (1954) 230–237
Bergen, Ben: Of sound, mind, and body: neural explanations for non-categorical phonology. PhD Thesis UC Berkeley (2001)
Bunt, Harry: Dialogue pragmatics and context specification. Computational Pragmatics, Abduction, Belief and Context; Studies in Computational Pragmatics. John Benjamins (2000) 81–150
Connolly, John: Context in the Study of Human Languages and Computer Programming Languages: A Comparison. Modeling and Using Context, Springer, LNCS (2001) 116–128
Cozman, Fabio: Generalizing Variable Elimination in Bayesian Networks. In Proc. of the IBERAMIA Workshop on Probabilistic Reasoning in Artificial Intelligence (2000)
Ebert, Christian and Shalom Lappin and Howard Gregory and Nicolas Nicolov: Generating Full Paraphrases out of Fragments in a Dialogue Interpretation System. In Proc. 2nd SIGdial Workshop (2001) 58–67
Fodor, Jerry: The Modularity of Mind. MIT Press (1983)
Gurevych Iryna, Rainer Malaka, Robert Porzel and Hans-Peter Zorn: Semantic Coherence Scoring Using an Ontology. In Proc. of the HLT-NAACL Conference (2003)
Gurevych Iryna and Michael Strube and Robert Porzel: Automatic Classification of Speech Recognition Hypothesis. In Proc. of the 3rd SIGdial Workshop (2002) 90–95
Johnston, Michael and Bangalore, Srinivas and Vasireddy, Gunaranjan and Stent, Amanda and Ehlen, Patrick and Walker, Marilyn and Whittaker, Steve and Maloor, Preetam: MATCH: An Architecture for Multimodal Dialogue Systems. Proceedings of ACL’02. (2002) 376–383
Langacker, Ronald: Conceptualization, symbolization and grammar. Cognitive and functional approaches to language structure. Laurence Erlbaum (1998)
Litman, D. and Walker, M. and Kearns, M.: Automatic Detection of Poor speech recognition at the dialogue Level In Proc. of ACL’99 (1999)
LuperFoy, Susann: The representation of multimodal user interface dialogues using discourse pegs. In Proceedings of ACL’92 (1992) 22–31
Narayanan, Srini and Daniel Jurafsky: Bayesian Models of Human Sentence Processing-. In Proc. 20th Cognitive Science Society Conference (1998) 84–90
Narayanan, Srinivas: KARMA: Knowledge-Based Active Representations for Metaphor and Aspect. PhD Thesis. UC Berkeley, (1997)
Oerder, Martin and Hermann Ney: Word Graphs: An Efficient Interface Between Continuous-Speech Recognition and Language Understanding. In Proc. of ICASSP Volume 2 (1993) 119–122
Paris, Cécile L.: User Modeling in Text Generation. Pinter (1993)
Poesio, Massimo: Scaling up Anahpora Resolution. In Proc. of the 1st Workshop on Scalable Natural Language Understanding (2002) 3–11
Porzel, Robert and Iryna Gurevych: Towards Context-adaptive Utterance Interpretation. In Proc. of the 3rd SIGdial Workshop (2002) 90–95
Porzel, Robert and John Bryant: Employing the Embodied Construction Grammar Formalism for Knowledge Represenation: The case of construal resolution. In Proc. of 8th International Conference on Cognitive Linguistic (2003)
Rapp, Stefan and Torge, Sunna and Goronzy, Silke and Kompe, Ralf: Dynamic speech interfaces In Proc. of 14th ECAI WS-AIMS (2000)
Russell, Stuart J. and Norvig, Peter: Artificial Intelligence. A Modern Approach. Prentice Hall (1995)
Robert Porzel and Michael Strube: Towards Context Adaptive Natural Language Processing Systems. In Proc. of the International Symposium: Computional Linguistics for the New Millenium (2000)
R. Schwartz and Y. Chow: The N-best Algorithm: an Efficient and Exact Procedure for Finding the N Most Likely Sentence Hypotheses. In Proc. of ICASSP’90 (1990)
Wolfgang Wahlster and Norbert Reithinger and Anselm Blocher: Smartkom: Multimodal Communication with a Life-Like Character. Proc. of the 7th Eurospeech (2001) 1547–1550
Marilyn A. Walker and Candace A. Kamm and Diane J. Litman: Towards Developing General Model of Usability with PARADISE. Natural Language Engeneering 6 (2000)
Patrick Henry Winston: Artificial Intelligence. Addison-Wesley (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Porzel, R., Gurevych, I. (2003). Contextual Coherence in Natural Language Processing. In: Blackburn, P., Ghidini, C., Turner, R.M., Giunchiglia, F. (eds) Modeling and Using Context. CONTEXT 2003. Lecture Notes in Computer Science(), vol 2680. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44958-2_22
Download citation
DOI: https://doi.org/10.1007/3-540-44958-2_22
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40380-7
Online ISBN: 978-3-540-44958-4
eBook Packages: Springer Book Archive