Word Confidence Estimation for SMT N-best List Re-ranking

Abstract : This paper proposes to use Word Confidence Estimation (WCE) information to improve MT outputs via N-best list re-ranking. From the confidence label assigned for each word in the MT hypothesis , we add six scores to the baseline log-linear model in order to re-rank the N-best list. Firstly, the correlation between the WCE-based sentence-level scores and the conventional evaluation scores (BLEU, TER, TERp-A) is investigated. Then, the N-best list re-ranking is evaluated over different WCE system performance levels: from our real and efficient WCE system (ranked 1st during last WMT 2013 Quality Estimation Task) to an oracle WCE (which simulates an interactive scenario where a user simply validates words of a MT hypothesis and the new output will be automatically regenerated). The results suggest that our real WCE system slightly (but significantly) improves the baseline while the oracle one extremely boosts it; and better WCE leads to better MT quality.
Type de document :
Communication dans un congrès
Proceedings of the Workshop on Humans and Computer-assisted Translation (HaCaT) during EACL, 2014, Gothenburg, Sweden. 2014
Liste complète des métadonnées

Littérature citée [27 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00953719
Contributeur : Laurent Besacier <>
Soumis le : vendredi 23 février 2018 - 12:46:01
Dernière modification le : jeudi 11 octobre 2018 - 08:48:03
Document(s) archivé(s) le : jeudi 24 mai 2018 - 21:25:26

Fichier

eacl2014_cameraready.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00953719, version 1

Citation

Ngoc-Quang Luong, Laurent Besacier, Benjamin Lecouteux. Word Confidence Estimation for SMT N-best List Re-ranking. Proceedings of the Workshop on Humans and Computer-assisted Translation (HaCaT) during EACL, 2014, Gothenburg, Sweden. 2014. 〈hal-00953719〉

Partager

Métriques

Consultations de la notice

529

Téléchargements de fichiers

21