Natural Language Processing

To meet with the needs of a fast-changing information society, man-machine interactions have to be made more efficient. One possible way of doing this is to make computers capable of understanding and responding human language.

Research Area

My research objectives in the field of Natural Language Processing are:

- building a Hungarian ontology
- the development of reliable Hungarian part-of-speech tagging and syntactic tree-building method
- automatic translation
- information extraction
- the application of machine learning (Kernel methods) to NLP problems

Selected Papers on the Topic

Csendes, D., Csirik, J., Gyimóthy, T., Kocsor, A.: The Szeged Treebank, in: V. Matousek et al. (Eds.): Proceedings of the 8th International Conference on Text, Speech and Dialogue, TSD 2005, LNAI 3658, pp. 123-131, Springer Verlag, 2005. [pdf][abstract][bib]

Hócza, A., Felföldi, L., Kocsor, A.: Learning Syntactic Patterns Using Boosting and Other Classifier Combination Schemas, in: V. Matousek et al. (Eds.): Proceedings of the 8th International Conference on Text, Speech and Dialogue, TSD 2005, LNAI 3658, pp. 69-76, Springer Verlag, 2005. [pdf][abstract][bib]

Csendes, D., Csirik, J., Kocsor, A.: The Szeged Treebank Project, accepted for Corpus Linguistics 2005, Birmingham, July 14th-17th, 2005. [pdf][abstract][bib]