Word Confidence Estimation and its Integration in Sentence Quality Estimation for Machine Translation

Abstract : This paper proposes some ideas to build an effective estima-tor, which predicts the quality of words in a Machine Translation (MT) output. We integrate a number of features of various types (system-based, lexical, syntactic and semantic) into the conventional feature set, for our baseline classifier training. Once having experiments with all features , we deploy a " Feature Selection " strategy to filter the best performing ones. Then, a method that combines multiple " weak " classifiers to build a strong " composite " classifier by taking advantage of their com-plementarity allows us achieve a better performance in term of F score. Finally, we exploit word confidence scores for improving the estimation system at sentence level.
Type de document :
Communication dans un congrès
Proceedings of the fifth international conference on knowledge and systems engineering (KSE), 2013, Hanoi, Vietnam. Proceedings of the fifth international conference on knowledge and systems engineering (KSE), pp.x-x, 2013
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00953774
Contributeur : Laurent Besacier <>
Soumis le : jeudi 23 novembre 2017 - 10:10:28
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03

Fichier

WordConfidenceEstimationAndIts...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00953774, version 1

Citation

Ngoc-Quang Luong, Laurent Besacier, Benjamin Lecouteux. Word Confidence Estimation and its Integration in Sentence Quality Estimation for Machine Translation. Proceedings of the fifth international conference on knowledge and systems engineering (KSE), 2013, Hanoi, Vietnam. Proceedings of the fifth international conference on knowledge and systems engineering (KSE), pp.x-x, 2013. 〈hal-00953774〉

Partager

Métriques

Consultations de la notice

356

Téléchargements de fichiers

59