Understanding the Impact of UGC Specificities on Translation Quality - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Understanding the Impact of UGC Specificities on Translation Quality

Résumé

This work takes a critical look at the evaluation of user-generated content automatic translation, the well-known specificities of which raise many challenges for MT. Our analyses show that measuring the average-case performance using a standard metric on a UGC test set falls far short of giving a reliable image of the UGC translation quality. That is why we introduce a new data set for the evaluation of UGC translation in which UGC specificities have been manually annotated using a fine-grained typology. Using this data set, we conduct several experiments to measure the impact of different kinds of UGC specificities on translation quality, more precisely than previously possible.

Dates et versions

hal-03540175 , version 1 (23-01-2022)

Identifiants

Citer

José Carlos Rosales Nunez, Djamé Seddah, Guillaume Wisniewski. Understanding the Impact of UGC Specificities on Translation Quality. W-NUT 2021 - Seventh Workshop on Noisy User-generated Text (colocated with EMNLP 2021), association for computational linguistics, Nov 2021, Punta Cana, Dominican Republic. ⟨hal-03540175⟩
77 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More