Abstract
This paper describes the team ("ODIANLP")'s submission to WAT 2020. We have participated in the EnglishRIGHTWARDS ARROWHindi Multimodal task and Indic task.
We have used the state-of-the-art Transformer model for the translation task and Inception ResNetV2 for the Hindi Image Captioning task. Our submission tops in EnglishRIGHTWARDS ARROWHindi Multimodal task in its track and OdiaLEFT RIGHT ARROW English translation tasks.
Also, our submissions performed well in the Indic Multilingual tasks.