REPORT Parida_Idiap-RR-10-2021/IDIAP NLPHut?s Participation at WAT2021 Parida, Shantipriya Panda, Subhadarshi Kotwal, Ketan Dash, Amulya Ratna Dash, Satya Ranjan Sharma, Yashvardhan Motlicek, Petr Bojar, Ondrej EXTERNAL http://publications.idiap.ch/attachments/reports/2021/Parida_Idiap-RR-10-2021.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/Parida_WAT2021_2021 Related documents Idiap-RR-10-2021 2021 Idiap July 2021 This paper provides the description of shared tasks to the WAT 2021 by our team NLPHut's. We have participated in the English→Hindi Multimodal translation task, English→Malayalam Multimodal translation task, and Indic Multi-lingual 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 English→Malayalam Multimodal translation task (text-only translation, and Malayalam caption), and ranks second-best in English→Hindi Multimodal translation task (text-only translation, and Hindi caption). Our submissions have also performed well in the Indic Multilingual translation tasks. CONF Parida_WAT2021_2021/IDIAP NLPHut's Participation at WAT2021 Parida, Shantipriya Panda, Subhadarshi Kotwal, Ketan Dash, Amulya Ratna Dash, Satya Ranjan Sharma, Yashvardhan Motlicek, Petr Bojar, Ondrej EXTERNAL http://publications.idiap.ch/attachments/papers/2021/Parida_WAT2021_2021.pdf PUBLIC http://publications.idiap.ch/index.php/publications/showcite/Parida_Idiap-RR-10-2021 Related documents Proceedings of the 8th Workshop on Asian Translation (WAT2021) 2021 Association for Computational Linguistics 146--154 978-1-954085-63-3 https://aclanthology.org/2021.wat-1.16/ URL This paper provides the description of shared tasks to the WAT 2021 by our team NLPHut's. We have participated in the English→Hindi Multimodal translation task, English→Malayalam Multimodal translation task, and Indic Multi-lingual 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 English→Malayalam Multimodal translation task (text-only translation, and Malayalam caption), and ranks second-best in English→Hindi Multimodal translation task (text-only translation, and Hindi caption). Our submissions have also performed well in the Indic Multilingual translation tasks.