Supported Languages

ROSANA is available for a wide class of languages:

ROSANA for English

This is the original version of ROSANA, the design, implementation, and evaluation of which constitutes the central part of my Ph. D. project. ROSANA for English works on the syntactic analyses generated by the robust FDG (Functional Dependency Grammar) parser of Timo Järvinen and Pasi Tapanainen. Details regarding the design and empirical evaluation of this version of ROSANA are given in various research papers (available ffor download in the publication section).

ROSANA for German

The system ROSANA-Deutsch works on the syntactic analyses generated by Connexor Machinese Syntax for German as of August 2005 (a descendant of the FDG parser). Due to the modular design of original ROSANA, which keeps apart the anaphor resolution core algorithm and the frontend for reading in syntactic analyses, adaptation efforts proved to be limited. The anaphor resolution core algorithm employed by ROSANA-Deutsch is virtually identical to the core algorithm of its ancestor.

ROSANA for other languages

The core algorithm of ROSANA is applicable to the wide class of languages for which the above mentioned antecedent constraints and preferences are suitable. Moreover, meanwhile (in 2005), Connexor Machinese Syntax has been made available for a plethora of languages, including English, French, German, Spanish, Italian, Dutch, Swedish, Danish, Norwegian, and Finnish. Hence, versions of ROSANA for these languages could be made available upon request, requiring adaptation works with an estimated volume of about six to twelve person weeks only.

Schreibe einen Kommentar