Domain-Specific Knowledge Acquisition and Classification Using WordNet
DAN I. MOLDOVAN, Roxana Gîrju · 2000
For many knowledge intensive applications, it is necessary to have extensive domain-specific knowledge in addition to general-purpose knowledge bases usually built around Machine Readable Dictionaries. This paper presents a methodology for acquiring domain specific knowledge from text and classifying the concepts learned into an ontology that extends WordNet. The method was tested for three seed concepts selected from the financial domain: interest rate, stock market, and ination. Queries were formed with each of these concepts and a small corpus of 500 sentences was extracted automatically from the Internet for each concept. The system learned a total of 151 new concepts and 69 new relations.