(Downloads - 0)
For more info about our services contact : help@bestpfe.com
Table of contents
Chapter 1 Theoretical Background & State-of-the-art
1.1 Introduction
1.2 Formal Concept Analysis
1.2.1 Implications, Denitions and Association Rules
1.2.2 Conceptual Stability
1.2.3 Many-valued Contexts
1.2.4 Conceptual Scaling
1.2.5 Calculating a concept lattice
1.2.6 Pattern structures
1.3 Information Retrieval
1.4 A survey on Formal Concept Analysis based Information Retrieval approaches
1.4.1 Pre-FCA history – A lattice to model the description and document spaces
1.4.2 FCA meets IR
1.4.3 Enriching the description space through external knowledge sources
1.4.4 Relevance Feedback and Automatic Retrieval
1.4.5 Applications and Systems
1.5 Conclusions
Chapter 2 Contributions on Retrieval
2.1 Prologue
2.2 Introduction
2.3 Background
2.3.1 Information content as a semantic relation measure
2.3.2 The principles of Concept Lattice-based Ranking
2.4 CLAIRE – Concept Lattices for Information Retrieval
2.4.1 Motivation for a new approach for Information Retrieval based on Formal Concept Analysis
2.4.2 The principles of CLAIRE
2.4.3 The implementation of CLAIRE as a Knowledge Discovery in Databases process
2.4.4 Step 1 – Document Classication
2.4.5 Step 2 – Concept Lattice Navigation
2.4.6 Step 3 – Formal Concept Ranking
2.5 Experimental Evaluation
2.5.1 Experimental setting
2.5.2 Evaluation measures
2.5.3 Results
2.5.4 Query analysis
2.6 Conclusions
Chapter 3 Contributions on Indexing
3.1 Introduction
3.2 Background
3.2.1 The vector space model for retrieval (VSM)
3.2.2 Interval Pattern Structures
3.2.3 Relational Concept Analysis (RCA)
3.3 CLAIRE and the vector space model
3.3.1 Querying
3.3.2 Retrieving documents with ip-CLAIRE
3.3.3 Experimental results
3.3.4 Discussion on the capabilities of ip-CLAIRE
3.4 A model for heterogeneous indexing
3.4.1 Inspiring problem – Latent Semantic Indexing
3.4.2 Adapting RCA for pattern structures
3.4.3 Discussion on the heterogeneous pattern structures model
3.5 Conclusions
Chapter 4 Beyond indexing: Biclustering and its applications
4.1 Introduction
4.2 Background
4.2.1 Biclustering
4.2.2 The links between FCA and biclustering
4.2.3 Triadic Concept Analysis
4.3 Biclustering using FCA
4.3.1 Biclustering using partitions
4.3.2 Formalizations
4.3.3 Partition Space and Partition Pattern Structures
4.3.4 Experiments
4.3.5 Discussion on Biclustering and FCA
4.4 FCA and Biclustering: Two additional models
4.4.1 Scaled Partition Pattern Structures
4.4.2 Interval Pattern Structure Approach
4.4.3 Triadic Concept Analysis Approach
4.4.4 Experiments
4.4.5 Discussion
4.5 Applications
4.5.1 Recommender Systems
4.5.2 Functional Dependencies
4.6 Conclusions
Conclusions and perspectives
Bibliography
