Learning Shallow Syntactic Dependencies from Imbalanced Datasets: A Case Study in Modern Greek and English

Abstract : The present work aims to create a shallow parser for Modern Greek subject/object detection, using machine learning techniques. The parser relies on limited resources. Experiments with equivalent input and the same learning techniques were conducted for English, as well, proving that the methodology can be adjusted to deal with other languages with only minor modifications. For the first time, the class imbalance problem concerning Modern Greek syntactically annotated data is successfully addressed.
Type de document :
Communication dans un congrès
Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-364 (Part II), pp.190-195, 2011, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-23960-1_23〉
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01571499
Contributeur : Hal Ifip <>
Soumis le : mercredi 2 août 2017 - 16:22:38
Dernière modification le : vendredi 1 décembre 2017 - 01:16:25

Fichier

978-3-642-23960-1_23_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Argiro Karozou, Katia Kermanidis. Learning Shallow Syntactic Dependencies from Imbalanced Datasets: A Case Study in Modern Greek and English. Lazaros Iliadis; Ilias Maglogiannis; Harris Papadopoulos. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. Springer, IFIP Advances in Information and Communication Technology, AICT-364 (Part II), pp.190-195, 2011, Artificial Intelligence Applications and Innovations. 〈10.1007/978-3-642-23960-1_23〉. 〈hal-01571499〉

Partager

Métriques

Consultations de la notice

71

Téléchargements de fichiers

13