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).
翻译:本文件对提交亚洲翻译讲习班的“Silo NLP”文件(WAT2022)的系统描述提供了系统描述,我们参加了印度多式任务(英语->Hindi、英语->Malayalam和英语->Bengali多式翻译);对于只翻译文本的翻译,我们从零到微调的MBART-50模型培训了变换器和微调的MBART-50模型;对于多式联运,我们使用同样的MBART结构以及从图像中提取的物体标记作为与文本序列相连接的视觉特征。我们提交的任务最多,包括英语- > Hindi多式翻译(评价测试)、英语- > Malayalam只读文本和多式翻译(评价测试)、英语- > Bengali多式翻译(挑战测试)和英语- > Bengali只读文本翻译(评价测试)。