Contextual coherence in natural language processing

作者: Robert Porzel , Iryna Gurevych

DOI: 10.1007/3-540-44958-2_22

关键词:

摘要: Controlled and restricted dialogue systems are reliable enough to be deployed in various real world applications. The more conversational a system becomes, the difficult unreliable become recognition processing. Numerous research projects struggling overcome problems arising with more- or truly system. We introduce set of contextual coherence measurements that can improve reliability spoken systems, by including knowledge at stages natural language processing pipeline. show that, situational successfully employed resolve pragmatic ambiguities it coupled ontological semantic choose among competing automatic speech hypotheses.

参考文章(27)
Wolfgang Wahlster, Anselm Blocher, Norbert Reithinger, Smartkom: multimodal communication with a life- like character. conference of the international speech communication association. pp. 1547- 1550 ,(2001)
Cecile L. Paris, User Modeling in Text Generation St. Martin's Press, Inc.. ,(1993)
R. Schwartz, Y.-L. Chow, The N-best algorithms: an efficient and exact procedure for finding the N most likely sentence hypotheses international conference on acoustics, speech, and signal processing. pp. 81- 84 ,(1990) , 10.1109/ICASSP.1990.115542
James Allen, Natural Language Understanding ,(1987)
Jerome A. Feldman, Srinivas Sankara Narayanan, Karma: knowledge-based active representations for metaphor and aspect University of California, Berkeley. ,(1997)
F. G. Cozman, Generalizing variable elimination in Bayesian networks Proc. IBERAMIA/SBIA-2000 Workshops (Workshop on Probabilistic Reasoning in Artificial Intelligence). ,(2000)
Robert Cummins, Jerry Fodor, The Modularity of Mind. The Philosophical Review. ,vol. 94, pp. 101- 108 ,(1985) , 10.2307/2184717
Iryna Gurevych, Rainer Malaka, Robert Porzel, Hans-Péter Zorn, Semantic coherence scoring using an ontology Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - NAACL '03. pp. 9- 16 ,(2003) , 10.3115/1073445.1073457