Learning Shallow Syntactic Dependencies from Imbalanced Datasets: A Case Study in Modern Greek and English - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2011

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

Argiro Karozou
  • Function : Author
  • PersonId : 1014237
Katia Lida Kermanidis
  • Function : Author
  • PersonId : 992337

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.
Fichier principal
Vignette du fichier
978-3-642-23960-1_23_Chapter.pdf (363.34 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01571499 , version 1 (02-08-2017)

Licence

Identifiers

Cite

Argiro Karozou, Katia Lida Kermanidis. Learning Shallow Syntactic Dependencies from Imbalanced Datasets: A Case Study in Modern Greek and English. 12th Engineering Applications of Neural Networks (EANN 2011) and 7th Artificial Intelligence Applications and Innovations (AIAI), Sep 2011, Corfu, Greece. pp.190-195, ⟨10.1007/978-3-642-23960-1_23⟩. ⟨hal-01571499⟩
98 View
100 Download

Altmetric

Share

More