Affiliation:
1. Université de Moncton, Canada
Abstract
In the context of the prodigious growth of network-based information services, messaging and edutainment, we introduce new tools that enable information management through the use of efficient multimodal interaction using natural language and speech processing. These tools allow the system to respond to close-to natural language queries by means of pattern matching. A new approach which gives the system the ability to learn new utterances of natural language queries from the user is presented. This automatic learning process is initiated when the system encounters an unknown command. This alleviates the burden of users learning a fixed grammar. Furthermore, this enables the system to better respond to spontaneous queries. This work investigates how an information system can benefit from the use of conversational agents to drastically decrease the cognition load of the user. For this purpose, Automated Service Agents and Artificial Intelligence Markup Language (AIML) are used to provide naturalness to the dialogs between users and machines.
Reference32 articles.
1. Aho, A. V., Sethi, R., & Ullman, J. D. (2006). Compilers: Principles, Techniques, and Tools. New York. Addison Wesley, 2nd edition.
2. ALICE. (2005). Artificial Intelligence Markup Language (AIML) Version 1.0.1, AI Foundation. Retrieved August 23, 2008, from http://alicebot.org/TR/2005/WD-aiml.
3. Toward conversational human-computer interaction.;J. F.Allen;AI Magazine,2001
4. Benahmed, Y., & Selouani, S. A. (2006). Robust Self-Training System for Spoken Query Information retrieval using Pitch Range Variations. Proceedings of IEEE Canadian Conference on Electrical and Computer Engineering (pp. 949-952). Ottawa, Canada.
5. Bouchet, J., & Nigay, L. (2004). ICARE: A Component-Based Approach for the Design and Development of Multimodal Interfaces. Extended Abstracts of International conference for human-computer interaction (pp. 1325-1328). CHI2004: Vienna, Austria.