Find The Errors, Get The Better: Enhancing Machine Translation via Word Confidence Estimation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Natural Language Engineering Année : 2017

Find The Errors, Get The Better: Enhancing Machine Translation via Word Confidence Estimation

Résumé

This article presents two novel ideas of improving the Machine Translation (MT) quality by applying the word-level quality prediction for the second pass of decoding. In this manner, the word scores estimated by Word Con dence Estimation (WCE) systems help to reconsider the MT hypotheses for selecting a better candidate rather than accepting the current sub-optimal one. In the rst attempt, the selection scope is limited to the MT N-best list, in which our proposed re-ranking features are combined with those of the decoder for re-scoring. Then, the search space is enlarged over the entire search graph, storing many more hypotheses generated during the rst pass of decoding. Over all paths containing words of the N-best list, we propose an algorithm to strengthen or weaken them depending on the estimated word quality. In both methods, the highest-score candidate after the search becomes the ocial translation. The results obtained show that both approaches advance the MT quality over the one-pass baseline, and the Search Graph Re-decoding achieves more gains (in BLEU score) than N-best List Re-ranking method.
Fichier principal
Vignette du fichier
papier_final.pdf (635.86 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01436779 , version 1 (09-11-2017)

Identifiants

  • HAL Id : hal-01436779 , version 1

Citer

Ngoc-Quang Luong, Laurent Besacier, Benjamin Lecouteux. Find The Errors, Get The Better: Enhancing Machine Translation via Word Confidence Estimation. Natural Language Engineering, 2017, 1, pp.1 - 24. ⟨hal-01436779⟩
424 Consultations
225 Téléchargements

Partager

Gmail Facebook X LinkedIn More