@inproceedings{aly-etal-2021-efficient,
    title = "Efficient Unsupervised {NMT} for Related Languages with Cross-Lingual Language Models and Fidelity Objectives",
    author = "Aly, Rami  and
      Caines, Andrew  and
      Buttery, Paula",
    editor = {Zampieri, Marcos  and
      Nakov, Preslav  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Tiedemann, J{\"o}rg  and
      Scherrer, Yves  and
      Jauhiainen, Tommi},
    booktitle = "Proceedings of the Eighth Workshop on NLP for Similar Languages, Varieties and Dialects",
    month = apr,
    year = "2021",
    address = "Kiyv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.vardial-1.6/",
    pages = "49--59",
    abstract = "The most successful approach to Neural Machine Translation (NMT) when only monolingual training data is available, called unsupervised machine translation, is based on back-translation where noisy translations are generated to turn the task into a supervised one. However, back-translation is computationally very expensive and inefficient. This work explores a novel, efficient approach to unsupervised NMT. A transformer, initialized with cross-lingual language model weights, is fine-tuned exclusively on monolingual data of the target language by jointly learning on a paraphrasing and denoising autoencoder objective. Experiments are conducted on WMT datasets for German-English, French-English, and Romanian-English. Results are competitive to strong baseline unsupervised NMT models, especially for closely related source languages (German) compared to more distant ones (Romanian, French), while requiring about a magnitude less training time."
}