Contextual Coherence in Natural Language Processing

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.

[1]  Y. Bar-Hillel.  Logical Syntax and Semantics , 1954 .

[2]  J. Fodor.  The Modularity of mind. An essay on faculty psychology , 1986 .

[3]  James F. Allen.  Natural language understanding , 1987, Bejnamin/Cummings series in computer science.

[4]  R. Schwartz,et al.  The N-best algorithms: an efficient and exact procedure for finding the N most likely sentence hypotheses , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[5]  Susann LuperFoy,et al.  The Representation of Multimodal User Interface Dialogues Using Discourse Pegs , 1992, ACL.

[6]  Cecile L. Paris.  User Modeling in Text Generation , 1993 .

[7]  Hermann Ney,et al.  Word graphs: an efficient interface between continuous-speech recognition and language understanding , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[8]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[9]  K. Upton,et al.  A modern approach , 1995 .

[10]  J. Feldman,et al.  Karma: knowledge-based active representations for metaphor and aspect , 1997 .

[11]  Marilyn A. Walker,et al.  Automatic Detection of Poor Speech Recognition at the Dialogue Level , 1999, ACL.

[12]  Patrick Brézillon,et al.  Modeling and Using Context , 1999, Lecture Notes in Computer Science.

[13]  Marilyn A. Walker,et al.  Towards developing general models of usability with PARADISE , 2000, Natural Language Engineering.

[14]  Fabio Gagliardi Cozman,et al.  Credal networks , 2000, Artif. Intell..

[15]  F. Cozman,et al.  Generalizing variable elimination in Bayesian networks , 2000 .

[16]  Harry Bunt,et al.  Dialogue pragmatics and context specification , 2000, Abduction, Belief and Context in Dialogue.

[17]  Shalom Lappin,et al.  Generating Full Paraphrases of Fragments in a Dialogue Interpretation System , 2001, SIGDIAL Workshop.

[18]  James F. Allen,et al.  An architecture for more realistic conversational systems , 2001, IUI '01.

[19]  Wolfgang Wahlster,et al.  Smartkom: multimodal communication with a life- like character , 2001, INTERSPEECH.

[20]  John H. Connolly,et al.  Context in the Study of Human Languages and Computer Programming Languages: A Comparison , 2001, CONTEXT.

[21]  G. Lakoff,et al.  Of sound, mind, and body: neural explanations for non-categorical phonology , 2001 .

[22]  Iryna Gurevych,et al.  Towards Context-adaptive Utterance Interpretation , 2002, SIGDIAL Workshop.

[23]  Michael Strube,et al.  Towards Context-adaptive Natural Language Processing Systems , 2002 .

[24]  Marilyn A. Walker,et al.  MATCH: An Architecture for Multimodal Dialogue Systems , 2002, ACL.

[25]  Iryna Gurevych,et al.  Semantic Coherence Scoring Using an Ontology , 2003, NAACL.