In Greek

In this paper, we present an integrated system of language technology modules used in information retrieval and extraction applications for Greek. The described system comprises a series of autonomous processing units based on machine learning algorithms and rule-based approaches, together with language resources adapted to the needs of specific processing stages. An XML annotation platform has been built, while processing tools, lexical resources and textual data communicate with each other via this platform. Editing/viewing tools have been implemented, endowed with functionalities that allow annotators to gain access to previous annotation levels as well as necessary lexical resources.