@inproceedings{jasim-etal-2020-phraseout,
    title = "{P}hrase{O}ut: A Code Mixed Data Augmentation Method for {M}ultilingual{N}eural Machine Tranlsation",
    author = "Jasim, Binu  and
      Namboodiri, Vinay  and
      Jawahar, C V",
    editor = "Bhattacharyya, Pushpak  and
      Sharma, Dipti Misra  and
      Sangal, Rajeev",
    booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
    month = dec,
    year = "2020",
    address = "Indian Institute of Technology Patna, Patna, India",
    publisher = "NLP Association of India (NLPAI)",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.icon-main.63/",
    pages = "470--474",
    abstract = "Data Augmentation methods for Neural Machine Translation (NMT) such as back- translation (BT) and self-training (ST) are quite popular. In a multilingual NMT system, simply copying monolingual source sentences to the target (Copying) is an effective data augmentation method. Back-translation aug- ments parallel data by translating monolingual sentences in the target side to source language. In this work we propose to use a partial back- translation method in a multilingual setting. Instead of translating the entire monolingual target sentence back into the source language, we replace selected high confidence phrases only and keep the rest of the words in the target language itself. (We call this method PhraseOut). Our experiments on low resource multilingual translation models show that PhraseOut gives reasonable improvements over the existing data augmentation methods."
}