Abstract - This paper provides an overview of the textual and lexical analysis tools implemented at the Institute of Computational Linguistics, which reflect the development of the studies and applications of the Institute from the pioneer stage of lexicography to its current state of progress. The analysis procedures coordinated and integrated in a system called PiSystem are presented, starting from the base element, DBT (Database Testuale), an analysis query system of textual material, with its correlated base functions. The procedures include the following: a) analysis of entire textual corpora; b) new international coding; d) text classification/lemmatization; computer-assisted lemmatization; automatic lemmatization; analysis, navigation and retrieval of linguistic information for lemmatized texts. DBT-DIG, a system specifically designed to deal with Digital Libraries (textual material in character and/or image format), with particular regard to the collection of periodicals available in libraries, is also presented. Other components of the Pi-System are illustrated in detail in articles in this volume: handling of multilingual environments; treatment of bilingual (Italian-Arabic) material; processing, analysis and navigation within the dialectal ALT (Atlante Lessicale Toscano) archive.
PiSystem: sistemi integrati per l'analisi testuale
Picchi E
2003
Abstract
Abstract - This paper provides an overview of the textual and lexical analysis tools implemented at the Institute of Computational Linguistics, which reflect the development of the studies and applications of the Institute from the pioneer stage of lexicography to its current state of progress. The analysis procedures coordinated and integrated in a system called PiSystem are presented, starting from the base element, DBT (Database Testuale), an analysis query system of textual material, with its correlated base functions. The procedures include the following: a) analysis of entire textual corpora; b) new international coding; d) text classification/lemmatization; computer-assisted lemmatization; automatic lemmatization; analysis, navigation and retrieval of linguistic information for lemmatized texts. DBT-DIG, a system specifically designed to deal with Digital Libraries (textual material in character and/or image format), with particular regard to the collection of periodicals available in libraries, is also presented. Other components of the Pi-System are illustrated in detail in articles in this volume: handling of multilingual environments; treatment of bilingual (Italian-Arabic) material; processing, analysis and navigation within the dialectal ALT (Atlante Lessicale Toscano) archive.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
