Bidirectional associative memories
IEEE Transactions on Systems, Man and Cybernetics
Design of a browsing interface for information retrieval
SIGIR '89 Proceedings of the 12th annual international ACM SIGIR conference on Research and development in information retrieval
International Journal of Man-Machine Studies
Information retrieval through hybrid navigation of lattice representations
International Journal of Human-Computer Studies
Journal of the American Society for Information Science
Formal Concept Analysis: Mathematical Foundations
Formal Concept Analysis: Mathematical Foundations
Conceptual Graphs and Formal Concept Analysis
ICCS '97 Proceedings of the Fifth International Conference on Conceptual Structures: Fulfilling Peirce's Dream
CEM-Visualisation and Discovery in Email
PKDD '00 Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery
Noun-phrase analysis in unrestricted text for information retrieval
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Feature selection and feature extraction for text categorization
HLT '91 Proceedings of the workshop on Speech and Natural Language
Representation of Concept Lattices by Bidirectional Associative Memories
Neural Computation
Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements
IEEE Transactions on Computers
Text retrieval with more realistic concept matching and reinforcement learning
Information Processing and Management: an International Journal
Hi-index | 0.00 |
The model described here is based on the theory of Formal Concept Analysis (FCA). Each document is represented in a Concept Lattice: a structured organisation of concepts according to a subsumption relation and is encoded in a Bidirectional Associative Memory (BAM): a two-layer heterogeneous neural network architecture. The document retrieval process is viewed as a continuous conversation between queries and documents, during which documents are allowed to learn a consistent set of significant concepts to help its retrieval. A reinforcement learning strategy based on relevance feedback information makes the similarity of relevant documents stronger and nonrelevant documents weaker for each query.