@inproceedings{nguyen-etal-2021-data,
    title = "Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution",
    author = "Nguyen, Toan Q.  and
      Murray, Kenton  and
      Chiang, David",
    editor = "Federico, Marcello  and
      Waibel, Alex  and
      Costa-juss{\`a}, Marta R.  and
      Niehues, Jan  and
      Stuker, Sebastian  and
      Salesky, Elizabeth",
    booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
    month = aug,
    year = "2021",
    address = "Bangkok, Thailand (online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.iwslt-1.33/",
    doi = "10.18653/v1/2021.iwslt-1.33",
    pages = "287--293",
    abstract = "In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for concatenation improving BLEU by about +1 across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting."
}