The SPECTRANS System Description for the WMT22 Biomedical Task - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

The SPECTRANS System Description for the WMT22 Biomedical Task

Résumé

This paper describes the SPECTRANS submission for the WMT 2022 biomedical shared task. We present the results of our experiments using the training corpora and the JoeyNMT (Kreutzer et al., 2019) and SYSTRAN Pure Neural Server/ Advanced Model Studio toolkits for the language directions English to French and French to English. We compare the predictions of the different toolkits. We also use JoeyNMT to fine-tune the model with a selection of texts from WMT, Khresmoi and UFAL data sets. We report our results and assess the respective merits of the different translated texts.
Fichier principal
Vignette du fichier
2022.wmt-1.82.pdf (1.18 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04073006 , version 1 (19-04-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04073006 , version 1

Citer

Nicolas Ballier, Jean-Baptiste Yunès, Guillaume Wisniewski, Lichao Zhu, Maria Zimina-Poirot. The SPECTRANS System Description for the WMT22 Biomedical Task. 2022 Seventh Conference on Machine Translation (WMT22), Association for Computational Linguistics, Dec 2022, Abu Dhabi, France. pp.895-900. ⟨hal-04073006⟩
27 Consultations
12 Téléchargements

Partager

Gmail Facebook X LinkedIn More