Domain-Specific Knowledge Acquisition and Classification Using WordNet

For manyknowledgeintensive applications, it is necessary to have extensive domain-specific knowledgein addition to general-purpose knowledge bases usually built around MachineReadable Dictionaries. This paper presents a methodology for acquiring domainspecific knowledge from text and classifying the concepts learned into an ontology that extends WordNet. The methodwastested for three seed concepts selected fromthe financial domain:interest rate, stock market, andinflation. Queries wereformed with each of these concepts and a small corpus of 500sentences wasextracted automatically from the Internet for each concept. Thesystem learned a total of 151 newconcepts and 69 new relations. Domain Knowledge The knowledge is infinite and no matter howlarge a knowledgebase becomes, it is not possible to store all the concepts and procedures for all domains. Even if that was possible, the knowledgeis generative and there are no guarantees that a system will have the latest information all the time...

• Type: Conference
• Year: 2000
• Where: FLAIRS
• Authors: Dan I. Moldovan, Roxana Girju
• Keywords: Artificial Intelligence, Automatic Knowledge Acquisition, FLAIRS 2000, General-purpose Knowledge Bases, Knowledge Base