SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Text Classification from Labeled and Unlabeled Documents using EM
Machine Learning - Special issue on information retrieval
Structural Graph Matching Using the EM Algorithm and Singular Value Decomposition
IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
Evolutionary computation: a unified approach
Proceedings of the 10th annual conference companion on Genetic and evolutionary computation
Inexact matching of ontology graphs using expectation-maximization
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Transductive learning for text classification using explicit knowledge models
PKDD'06 Proceedings of the 10th European conference on Principle and Practice of Knowledge Discovery in Databases
| Hi-index | 0.00 |
This work presents an evolutionary algorithm for automatic ontology mapping, which attempts to map similar objects based on their hierarchical structures from an unclassified to a classified ontology. Alignment is performed by swapping branches between the two ontologies and comparing their similarities to find possible missing terms in the unclassified ontology. Our algorithm is a stochastic implementation of the expectation maximization (EM) algorithm, which attempts to find and insert possibly missing terms, and measures the resulting improvements through iterative E-steps and M-steps. Our approach evolves the E-step to find these terms, while the M-step maps the classified ontology onto the unclassified one. Only taxonomic information is evaluated. We extract high-level descriptions of low-level definitions, and create subsections of the search-spaces, and thus obtain a satisfactory representation of the entire search-space to sample.