Developing a Dialog System for New Idea Generation Support
A knowledge-based dialog system gives correct answers; however, it is unsuitable for open-ended input. On the other hand, Eliza makes open-ended conversations, but it gives no new information to its user. We propose a new type of dialog system. Our system lies between the above two dialog systems, and it converses about various topics and gives information related to the user’s utterances. This type of dialog is useful for generating new ideas especially when the user has an obscure desire to get information about his or her interest, but no concrete goal. Our system selects an appropriate sentence from a corpus to respond to a user’s utterance. The most proper response will have surface cohesion and semantic coherence with the user’s utterance. We made a trial system to converse about movies.
KeywordsNoun Phrase Trial System Centralness Ranking Surface Cohesion Dialog System
Unable to display preview. Download preview PDF.
- 2.Zue, V., Seneff, S., Glass, J., Polifroni, J., Pao, C., Hanzen, T., Hetherington, L.: Jupiter: A telephone-based conversational interface for weather information. IEEE Trans. SAP 8, 100–112 (2000)Google Scholar
- 4.Walker, M., Iida, M., Cote, S.: Japanese discourse and the process of centering. Computational Linguistics 20, 193–233 (1994)Google Scholar
- 5.Fujii, A., Inui, K., Tokunaga, T., Tanaka, H.: Case contribution in example-based verb sense disambiguation. Journal of Natural Language Processing 4, 111–123 (1997)Google Scholar
- 6.Kawahara, D., Kurohashi, S.: Improving japanese zero pronoun resolution by global word sense disambiguation. In: Proc. of the 20th COLING, pp. 343–349 (2004)Google Scholar
- 7.Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? sentiment classification using machine learning techniques. In: Proc. of the 40th ACL, pp. 417–424 (2002)Google Scholar