Learning to case-tag modern greek text

Authors:
Antonis Koursoumis;Evangelia Gkatzou;Antigoni M. Founta;Vassiliki I. Mavriki;Karolos Talvis;Spyros Mprilis;Ahmad A. Aliwat;Katia Lida Kermanidis
Affiliations:
Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece;Department of Informatics, Ionian University, Corfu, Greece
Venue:
SETN'12 Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applications
Year:
2012

Citing 3
Cited 0

Transformation-based error-driven learning and natural language processing: a case study in part-of-speech tagging

Computational Linguistics
Icelandic data driven part of speech tagging

HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Tagging Icelandic text using a linguistic and a statistical tagger

NAACL-Short '07 Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Companion Volume, Short Papers

Quantified Score

Hi-index	0.00

Visualization

Abstract

Morphological case tagging is essential for the identification of the syntactic and semantic roles of sentence constituents in most inflectional languages. Although it is usually viewed as a side-task of general tagging applications, it is addressed in the present work as an individual, stand-alone application. Supervised learning is applied to Modern Greek textual data in order to case-tag declinable words using merely elementary lexical information and local context. Several experiments with various context window sizes, as well as base- and meta-learning schemata, were run with promising results.