Using a Machine Learning Model to Assess the Complexity of Stress Systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Using a Machine Learning Model to Assess the Complexity of Stress Systems

Résumé

We address the task of stress prediction as a sequence tagging problem. We present sequential models with averaged perceptron training for learning primary stress in Romanian words. We use character n-grams and syllable n-grams as features and we account for the consonant-vowel structure of the words. We show in this paper that Romanian stress is predictable, though not deterministic, by using data-driven machine learning techniques.

Domaines

Linguistique
Fichier principal
Vignette du fichier
LREC_2014_paper.pdf (125.98 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01095427 , version 1 (15-12-2014)

Identifiants

  • HAL Id : hal-01095427 , version 1

Citer

L. Dinu, Alina Maria Ciobanu, Ioana Chitoran, Vlad Niculae. Using a Machine Learning Model to Assess the Complexity of Stress Systems. LREC 9, 2014, May 2014, Reykjavik, Iceland. ⟨hal-01095427⟩
90 Consultations
188 Téléchargements

Partager

Gmail Facebook X LinkedIn More