An instructable, adaptive interface for discovering and monitoring information on the World-Wide Web
- 1 December 1998
- proceedings article
- Published by Association for Computing Machinery (ACM)
- p. 157-160
- https://doi.org/10.1145/291080.291106
Abstract
We are creating a customizable, intelligent interface to the World-Wide Web that assists a user in locating spe-cific, current, and relevant information. sin Adaptive Web Assistant (WAWA) is capable of ac-cepting instructions regarding what type of information that users are seeking and how to go about looking for it. WAWA compiles these instructions into neural net-works, which means that the system's behavior can be modified via training examples. Users can create these training examples by rating pages retrieved by WAWA, but more importantly the system uses techniques from reinforcement learning to internally create its own ex-amples (users can also later provide additional instruc-tions). WAWA uses these neural networks to guide its autonomous navigation of the Web, thereby producing an interface to the Web that users periodically instructKeywords
This publication has 6 references indexed in Scilit:
- Creating advice-taking reinforcement learnersMachine Learning, 1996
- WordNetCommunications of the ACM, 1995
- Knowledge-based artificial neural networksArtificial Intelligence, 1994
- Developments in Automatic Text RetrievalScience, 1991
- Learning to Predict by the Methods of Temporal DifferencesMachine Learning, 1988
- Learning representations by back-propagating errorsNature, 1986