Silo NLP's Participation at WAT2022
This work addresses translation challenges for Indic languages, but it is incremental as it applies existing methods like Transformers and mBART with visual features to new tasks.
The paper describes a system for Indic multimodal translation tasks at WAT2022, achieving top results in multiple categories, including English->Hindi multimodal translation and English->Malayalam text-only and multimodal translation.
This paper provides the system description of "Silo NLP's" submission to the Workshop on Asian Translation (WAT2022). We have participated in the Indic Multimodal tasks (English->Hindi, English->Malayalam, and English->Bengali Multimodal Translation). For text-only translation, we trained Transformers from scratch and fine-tuned mBART-50 models. For multimodal translation, we used the same mBART architecture and extracted object tags from the images to use as visual features concatenated with the text sequence. Our submission tops many tasks including English->Hindi multimodal translation (evaluation test), English->Malayalam text-only and multimodal translation (evaluation test), English->Bengali multimodal translation (challenge test), and English->Bengali text-only translation (evaluation test).