Why Predicting Post-Edition is so Hard? Failure Analysis of LIMSI Submission to the APE Shared Task - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Why Predicting Post-Edition is so Hard? Failure Analysis of LIMSI Submission to the APE Shared Task

Résumé

This paper describes the two systems submitted by LIMSI to the WMT’15 Shared Task on Automatic Post-Editing. The first one relies on a reformulation of the APE task as a Machine Translation task; the second implements a simple rule-based approach. Neither of these two systems manage to improve the automatic translation. We show, by carefully analyzing the failure of our systems that this counter- performance mainly results from the inconsistency in the annotations.
Fichier principal
Vignette du fichier
W15-3027.pdf (125.76 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01635022 , version 1 (14-11-2017)

Identifiants

  • HAL Id : hal-01635022 , version 1

Citer

Guillaume Wisniewski, Nicolas Pécheux, François Yvon. Why Predicting Post-Edition is so Hard? Failure Analysis of LIMSI Submission to the APE Shared Task. Tenth Workshop on Statistical Machine Translation, Association for Computational Linguistics, Sep 2015, Lisbon, Portugal. pp.222 - 227. ⟨hal-01635022⟩
55 Consultations
98 Téléchargements

Partager

Gmail Facebook X LinkedIn More