An Information-Theoretic Definition of Similarity
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Automatic acquisition of hyponyms from large text corpora
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Ontology Learning and Population from Text: Algorithms, Evaluation and Applications
Ontology Learning and Population from Text: Algorithms, Evaluation and Applications
Learning non-taxonomic relationships from web documents for domain ontology construction
Data & Knowledge Engineering
YAGO: A Large Ontology from Wikipedia and WordNet
Web Semantics: Science, Services and Agents on the World Wide Web
Proceedings of the 2008 conference on Ontology Learning and Population: Bridging the Gap between Text and Knowledge
Unsupervised Learning of Semantic Relations for Molecular Biology Ontologies
Proceedings of the 2008 conference on Ontology Learning and Population: Bridging the Gap between Text and Knowledge
Deriving a large scale taxonomy from Wikipedia
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Learning concept hierarchies from text corpora using formal concept analysis
Journal of Artificial Intelligence Research
Distinguishing between instances and classes in the wikipedia taxonomy
ESWC'08 Proceedings of the 5th European semantic web conference on The semantic web: research and applications
Learning semantic n-ary relations from Wikipedia
DEXA'10 Proceedings of the 21st international conference on Database and expert systems applications: Part I
| Hi-index | 0.00 |
The key step for implementing the idea of the Semantic Web into a feasible system is providing a variety of domain ontologies that are constructed on demand, in an automated manner and in a very short time. In this paper we introduce an unsupervised method for constructing domain ontology taxonomies from Wikipedia. The benefit of using Wikipedia as the source is twofold: first, the Wikipedia articles are concise and have a particularly high "density" of domain knowledge; second, the articles represent a consensus of a large community, thus avoiding term disagreements and misinterpretations. The taxonomy construction algorithm, aimed at finding the subsumption relation, is based on two different techniques, which both apply linguistic parsing: analyzing the first sentence of each Wikipedia article and processing the categories associated with the article. The method has been evaluated against human judgment for two independent domains and the experimental results have proven its robustness and high precision.