Skip to Main Content
An automatic semantic term-network construction system is implemented in this research. This system uses the statistical values of the terms appeared in a document corpus. The term to term relationships in the term-network are decided by the similarities between term and term vectors. In order to measure the performance of our system, a standard data collection set, Reuters-21578, is used and about 2000 terms are extracted from the set automatically. The system is able to show the results as quickly as a real-time system. This term-network construction could be expected to quite easily apply to constructing the ontology system and to supporting the semantic retrieval system in the near future.