LORIA System for the WMT15 Quality Estimation Shared Task

Abstract : 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.
Type de document :
Communication dans un congrès
Workshop on Statistical Machine Translation, Sep 2015, Lisbonne, Portugal. Association for Computational Linguistics, pp.8, 2015, Proceedings of the Tenth Workshop on Statistical Machine Translation. 〈http://www.statmt.org/wmt15/〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01262104
Contributeur : David Langlois <>
Soumis le : mardi 26 janvier 2016 - 11:28:51
Dernière modification le : lundi 24 septembre 2018 - 09:04:03

Identifiants

  • HAL Id : hal-01262104, version 1

Collections

Citation

David Langlois. LORIA System for the WMT15 Quality Estimation Shared Task. Workshop on Statistical Machine Translation, Sep 2015, Lisbonne, Portugal. Association for Computational Linguistics, pp.8, 2015, Proceedings of the Tenth Workshop on Statistical Machine Translation. 〈http://www.statmt.org/wmt15/〉. 〈hal-01262104〉

Partager

Métriques

Consultations de la notice

77