作者: Antonino Mazzeo , Flora Amato , Sergio Scippacercola
DOI: 10.1285/I2037-3627V2N1P54
关键词:
摘要: In this work, a methodology for semi-automatic derivation of knowledge from document collections is proposed. order to extract relevant information documents, process integrating both statistical and lexical approaches applied. We propose strategy the semantic evaluation index terms extracted in ensure good correspondence between searched retrieved. Therefore, we system peculiar lexicon extraction assessment. The can be used defining an ontological model the processing corpus documents belonging a specialist domain.