BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation
This work addresses the need for better multimodal translation datasets for researchers, though it is incremental as it builds on existing datasets like How2 and VaTeX.
The authors tackled the problem of multimodal machine translation by introducing BigVideo, a large-scale dataset with 4.5 million sentence pairs and 9,981 hours of videos, and showed that visual information consistently improves translation models, with gains in BLEU, BLEURT, and COMET scores on both ambiguous and unambiguous test sets.
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.