LIUM’s Contributions to the WMT2019 News Translation Task: Data and Systems for German-French Language Pairs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

LIUM’s Contributions to the WMT2019 News Translation Task: Data and Systems for German-French Language Pairs

Résumé

This paper describes the neural machine translation (NMT) systems of the LIUM Laboratory developed for the French↔German news translation task of the Fourth Conference onMachine Translation (WMT 2019). The chosen language pair is included for the first time in the WMT news translation task. We de-scribe how the training and the evaluation data was created. We also present our participation in the French↔German translation directions using self-attentional Transformer networks with small and big architectures.
Fichier non déposé

Dates et versions

hal-02405788 , version 1 (11-12-2019)

Identifiants

Citer

Fethi Bougares, Jane Wottawa, Anne Baillot, Loïc Barrault, Adrien Bardet. LIUM’s Contributions to the WMT2019 News Translation Task: Data and Systems for German-French Language Pairs. Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), Aug 2019, Florence, France. pp.129-133, ⟨10.18653/v1/W19-5307⟩. ⟨hal-02405788⟩
74 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More