论文信息 - A Semi-automatic Ontology Learning Based on WordNet and Event-based Natural Language Processing

A Semi-automatic Ontology Learning Based on WordNet and Event-based Natural Language Processing

Ontology is more and more popular in all kinds of knowledge management system, but the manual acquisition of ontologies still remains a tedious, cumbersome task. Meanwhile moving toward semi-automation or automation of ontology construction is a solution. In this paper, we proposed a semiautomatic ontology building approach. In this approach the system starts form a small core ontology constructed by domain experts and learns the concepts and taxonomic and non-taxonomic relations by use of the general ontology WordNet and event-based natural language processing technologies automatically to construct the aim ontology. Our experimental results indicate that the method offers an improvement in quality of ontology and reduction in the time-consumed.

[1] Beth Levin,et al. English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[2] Steffen Staab,et al. Ontology Learning for the Semantic Web , 2002, IEEE Intell. Syst..

[3] Raphael Volz,et al. Semi-automatic Ontology Acquisition from a Corporate Intranet , 2000 .

[4] Thomas R. Gruber,et al. A translation approach to portable ontology specifications , 1993, Knowl. Acquis..

[5] Stefan Schulz,et al. Towards Very Large Terminological Knowledge Bases: A Case Study from Medicine , 2000, Canadian Conference on AI.

[6] Vasileios Hatzivassiloglou,et al. Domain -independent detection, extraction, and labeling of Atomic Events , 2003 .

[7] M. A. Jones. Tense, aspect and mood , 1996 .

[8] David Faure,et al. First experiences of using semantic knowledge learned by ASIUM for information extraction task using INTEX , 2000, ECAI Workshop on Ontology Learning.