Adaptive information retrieval: using a connectionist representation to retrieve and learn about documents
- 1 May 1989
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGIR Forum
- Vol. 23 (SI) , 11-20
- https://doi.org/10.1145/75335.75337
Abstract
AIR represents a connectionist approach to the task of information retrieval. The system uses relevance feedback from its users to change its representation of authors, index terms and documents so that, over time, AIR improves at its task. The result is a representation of the consensual meaning of keywords and documents shared by some group of users. The central focus goal of this paper is to use our experience with AIR to highlight those characteristics of connectionist representations that make them particularly appropriate for IR applications. We argue that this associative representation is a natural generalization of traditional IR techniques, and that connectionist learning techniques are effective in this setting.Keywords
This publication has 13 references indexed in Scilit:
- Connectionist learning proceduresArtificial Intelligence, 1989
- Legal information retrieval a hybrid approachPublished by Association for Computing Machinery (ACM) ,1989
- Parallel text search methodsCommunications of the ACM, 1988
- Knowledge representation, connectionism and conceptual retrievalPublished by Association for Computing Machinery (ACM) ,1988
- Information retrieval by constrained spreading activation in semantic networksInformation Processing & Management, 1987
- Collective Computation in Neuronlike CircuitsScientific American, 1987
- Parallel free-text search on the connection machine systemCommunications of the ACM, 1986
- Indexing and abstracting by associationAmerican Documentation, 1962
- Semantic Road Maps for Literature SearchersJournal of the ACM, 1961
- The Association Factor in Information RetrievalJournal of the ACM, 1961