Call: WAT2021 Multi-Modal Arabic-English Translation (ArEnMulti30K) Task
Call for Participation: WAT2021 Multi-Modal Arabic-English Translation (ArEnMulti30K) Task
We invite you to take part in one or both of the two following tasks organized as part of the Workshop on Asian Translation (WAT). The aim of the “WAT 2021 Multi-Modal translation task” is to enable research on multilingual multi-modal NLP.
The Workshop on Asian Translation (WAT) is organizing the multi-modal Arabic-to-English and English-to-Arabic translation tasks using the Multi30K dataset. Each task has two versions: constrained and unconstrained, and you are invited to participate in all of them. In the constrained versions, external resources such as additional datasets and pre-trained models with external data, are not allowed to be used except for preprocessing and visualization purposes. The Multi30K dataset is an extension of the Flicker30K dataset that provides 31,014 images along with five descriptions for each image in English. One of the five English descriptions was professionally translated by human experts to German, French and Czech. For this task, we have extended the Multi30K by providing an additional translation in Arabic. The target of this task is to focus on the translation between English and Arabic. However, participating teams are allowed and encouraged to benefit from the multi-modal and multi-lingual nature of the dataset, even in the constrained versions.
Please refer to the task website.
Roweida Mohammed, Jordan University of Science and Technology, Jordan
Inad Aljarrah, Jordan University of Science and Technology, Jordan
Mahmoud Al-Ayyoub, Jordan University of Science and Technology, Jordan
Ali Fadel, Jordan University of Science and Technology, Jordan