The Annotation Corpora of Text (ACT) Tool

Scripta & e-Scripta vol 2, 2004
  • Author(s):
  • Subject(s): Language and Literature Studies // Medieval slavic manuscripts // Annotation corpora // network & lexicographic applications //
  • Published by: Institute for Literature BAS
  • Print ISSN: 1312-238X
  • Summary/Abstract:

    The article presents a description of a computer application, developed by a team of authors at the Charles University in Prague, meant to support a multiaspect processing of examples of the cultural heritage in the intelligent environment of the information technologies. Provided is a possibility for the application to be used when describing and analyzing medieval manuscripts, experimented in the project of the Faculty of Mathematics and Physics Annotation corpora of Text (ACT, see The system is a linguistically-independent product for lexical and corpora processing of written texts. It has been created with the purpose to process large corpora with linguistic annotation, which mostly includes lexicographic and morphological analysis, and the syntactic and semantic information is marked on basic level. The system allows the users when working at different places, to compare the data between one another, and to keep the results regardless of the number of specialists working at the same time. A product which completely solves the problems of the linguistic analysis of medieval records with the help of computers is offered.