@inproceedings{gupta-etal-2021-vita,
title = "{V}i{TA}: Visual-Linguistic Translation by Aligning Object Tags",
author = "Gupta, Kshitij and
Gautam, Devansh and
Mamidi, Radhika",
editor = "Nakazawa, Toshiaki and
Nakayama, Hideki and
Goto, Isao and
Mino, Hideya and
Ding, Chenchen and
Dabre, Raj and
Kunchukuttan, Anoop and
Higashiyama, Shohei and
Manabe, Hiroshi and
Pa, Win Pa and
Parida, Shantipriya and
Bojar, Ond{\v{r}}ej and
Chu, Chenhui and
Eriguchi, Akiko and
Abe, Kaori and
Oda, Yusuke and
Sudoh, Katsuhito and
Kurohashi, Sadao and
Bhattacharyya, Pushpak",
booktitle = "Proceedings of the 8th Workshop on Asian Translation (WAT2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/fix-sig-urls/2021.wat-1.19/",
doi = "10.18653/v1/2021.wat-1.19",
pages = "166--173",
abstract = "Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality datasets to illustrate the contribution of visual modality in the translation systems. In this paper, we propose our system under the team name Volta for the Multimodal Translation Task of WAT 2021 from English to Hindi. We also participate in the textual-only subtask of the same language pair for which we use mBART, a pretrained multilingual sequence-to-sequence model. For multimodal translation, we propose to enhance the textual input by bringing the visual information to a textual domain by extracting object tags from the image. We also explore the robustness of our system by systematically degrading the source text. Finally, we achieve a BLEU score of 44.6 and 51.6 on the test set and challenge set of the multimodal task."
}
Markdown (Informal)
[ViTA: Visual-Linguistic Translation by Aligning Object Tags](https://preview.aclanthology.org/fix-sig-urls/2021.wat-1.19/) (Gupta et al., WAT 2021)
ACL