Communication Dans Un Congrès Année : 2017

Evaluating the morphological competence of Machine Translation Systems

Résumé

While recent changes in Machine Translation state-of-the-art brought translation quality a step further, it is regularly acknowledged that the standard automatic metrics do not provide enough insights to fully measure the impact of neural models. This paper proposes a new type of evaluation focused specifically on the morphological competence of a system with respect to various grammatical phenomena. Our approach uses automatically generated pairs of source sentences, where each pair tests one morphological contrast. This methodology is used to compare several systems submitted at WMT'17 for English into Czech and Latvian.

Fichier principal
Vignette du fichier
W17-4705.pdf (185.72 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence
Loading...

Dates et versions

hal-01618387 , version 1 (19-10-2017)

Licence

Identifiants

Citer

Franck Burlot, François Yvon. Evaluating the morphological competence of Machine Translation Systems. 2nd Conference on Machine Translation (WMT17), Association for Computational Linguistics, Sep 2017, Copenhague, Denmark. pp.43-55, ⟨10.18653/v1/W17-4705⟩. ⟨hal-01618387⟩
481 Consultations
332 Téléchargements

Altmetric

Partager

  • More