We present a large-scale video subtitle translation dataset, BigVideo, to facilitate the study of multi-modality machine translation. Compared with the widely used How2 and VaTeX datasets, BigVideo is more than 10 times larger, consisting of 4.5 million sentence pairs and 9,981 hours of videos. We also introduce two deliberately designed test sets to verify the necessity of visual information: Ambiguous with the presence of ambiguous words, and Unambiguous in which the text context is self-contained for translation. To better model the common semantics shared across texts and videos, we introduce a contrastive learning method in the cross-modal encoder. Extensive experiments on the BigVideo show that: a) Visual information consistently improves the NMT model in terms of BLEU, BLEURT, and COMET on both Ambiguous and Unambiguous test sets. b) Visual information helps disambiguation, compared to the strong text baseline on terminology-targeted scores and human evaluation. Dataset and our implementations are available at https://github.com/DeepLearnXMU/BigVideo-VMT.

本研究提出了一个大规模的视频字幕翻译数据集BigVideo，用于促进多模态机器翻译的研究；在跨模态编码器中引入了对比学习方法，结果表明视觉信息能够显著提高NMT模型的性能并帮助消除歧义。

BigVideo：一份大规模视频字幕翻译数据集，用于多模式机器翻译