Semi automatic extraction of a peculiar vucabulary in notary domain

摘要: En The bureaucratic domain and the notary one, in particular, are characterized by a huge amount of unstructured information. In order to opportunely manage knowledge contained within these documents for structuring, indexing retrieval purposes, suitable semantic-lexical approach requires vocabulary useful quick identification relevant information. In this paper we provide description system semi-automatic extraction terminological vocabulary, representative domain, based on analysis processing significant collection documents. addition, extracted peculiar lexicon will basis construction conceptual system, able perform semantic document contents.