LORIA System for the WMT15 Quality Estimation Shared Task - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

LORIA System for the WMT15 Quality Estimation Shared Task

Résumé

We describe our system for WMT2015 Shared Task on Quality Estimation, task 1, sentence-level prediction of post-edition effort. We use baseline features, Latent Semantic Indexing based features and features based on pseudo-references. SVM algorithm allows to estimate the linear regression between the features vectors and the HTER score. We use a selection algorithm in order to put aside needless features. Our best system leads to a performance in terms of Mean Absolute Error equal to 13.34 on official test while the official baseline system leads to a performance equal to 14.82.
Fichier non déposé

Dates et versions

hal-01262104 , version 1 (26-01-2016)

Identifiants

  • HAL Id : hal-01262104 , version 1

Citer

David Langlois. LORIA System for the WMT15 Quality Estimation Shared Task. Workshop on Statistical Machine Translation, Sep 2015, Lisbonne, Portugal. pp.8. ⟨hal-01262104⟩
73 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More