RoCS-MT: Robustness Challenge Set for Machine Translation
RoCS-MT, a Robust Challenge Set for Machine Translation (MT), is designed to test MT
systems' ability to translate user-generated content (UGC) that displays non-standard …
systems' ability to translate user-generated content (UGC) that displays non-standard …
Multi-way Variational NMT for UGC: Improving Robustness in Zero-shot Scenarios via Mixture Density Networks
This work presents a novel Variational Neural Machine Translation (VNMT) architecture with
enhanced robustness properties, which we investigate through a detailed case-study …
enhanced robustness properties, which we investigate through a detailed case-study …
Machine Translation of User-Generated Contents: an Evaluation of Neural Translation Systems under Zero-shot Conditions
JR Núñez - 2023 - theses.hal.science
The rapid advancements in telecommunications over the past few decades have
revolutionized the way people exchange information. Thanks to these advancements, the …
revolutionized the way people exchange information. Thanks to these advancements, the …
Normalisation lexicale de contenus générés par les utilisateurs sur les réseaux sociaux
L Nishimwe - Actes de CORIA-TALN 2023. Actes des 16e …, 2023 - hal.science
L'essor du traitement automatique des langues (TAL) se vit dans un monde où l'on produit
de plus en plus de contenus en ligne. En particulier sur les réseaux sociaux, les textes …
de plus en plus de contenus en ligne. En particulier sur les réseaux sociaux, les textes …