Abstract
This paper provides the description of shared tasks to the WAT 2021 by our team "NLPHut". We have participated in the EnglishRIGHTWARDS ARROWHindi Multimodal translation task, EnglishRIGHTWARDS ARROWMalayalam Multimodal translation task, and Indic Multilingual translation task.
We have used the state-of-the-art Transformer model with language tags in different settings for the translation task and proposed a novel "region-specific" caption generation approach using a combination of image CNN and LSTM for the Hindi and Malayalam image captioning. Our submission tops in EnglishRIGHTWARDS ARROWMalayalam Multimodal translation task (text-only translation, and Malayalam caption), and ranks secondbest in EnglishRIGHTWARDS ARROWHindi Multimodal translation task (text-only translation, and Hindi caption).
Our submissions have also performed well in the Indic Multilingual translation tasks.