The purpose of automatic keyphrase extraction is to provide a set of concepts representative of the content of the document on the basis of the text of the document. In one of the SemEval-2 tasks, keywords had to be assigned to scientific publications written in English. The system developed at our group performed very well at this challenge, moreover, the first steps were also taken toward adapting the system to Hungarian.

References

• Berend, Gábor; Farkas, Richárd 2010: SZTERGAK: Feature Engineering for Keyphrase Extraction. In: Proceedings of SemEval-2010, Uppsala, Sweden.
• Berend Gábor, Farkas Richárd 2010: Kulcsszókinyerés magyar nyelvû tudományos publikációkból. In: Tanács Attila, Vincze Veronika (szerk.): VII. Magyar Számítógépes Nyelvészeti Konferencia. Szeged, Szegedi Tudományegyetem, pp. 47-55.

For further information please contact Gábor Berend (berendg AT inf.u-szeged.hu).