Top-down natural language query approach for embodied conversational agent
Goh, O.S., Depickere, A., Fung, C.C. and Wong, K.W. (2006) Top-down natural language query approach for embodied conversational agent. In: International MultiConference of Engineers and Computer Scientists (IMECS 2006), 27-29 June 2006, Hong Kong.
Download (202kB) | Preview
This paper describes research work in implementing a conversational intelligent agent on the web focusing on a top-down natural language query approach. While the present World-Wide Web provides a distributed hypermedia interface to the vast amount of information on the Internet, there is a lack of appropriate metadata to that content. Instead of being a giant library as intended, increasing sections of the Web are looking like a giant dump. A multi-level natural language query system is described in this paper for the representation of knowledge in specific and open domains. The six layers system includes spell check, Natural Language Understanding and Reasoning, FAQChat, Metadata Index Search, Pattern matching and case-based reasoning, and, semi-automated matching approach. Extracts from queries on the field of pandemic crisis, Bird Flu H5N1 is demonstrated.
|Publication Type:||Conference Paper|
|Murdoch Affiliation:||School of Information Technology|
|Publisher:||International Association of Engineers (IAENG)|
|Item Control Page|
Downloads per month over past year