@article{witwikipediabasedimagetextdatasetfor,
  title = {WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning},
  author = {Krishna Srinivasan and Karthik Raman and Jiecao Chen and Michael Bendersky and Marc Najork},
  year = {2021},
  eprint = {2103.01913},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2103.01913v2},
}