@inproceedings{costa-jussa-de-jorge-2020-fine,
    title = "Fine-tuning Neural Machine Translation on Gender-Balanced Datasets",
    author = "Costa-juss{\`a}, Marta R.  and
      de Jorge, Adri{\`a}",
    editor = "Costa-juss{\`a}, Marta R.  and
      Hardmeier, Christian  and
      Radford, Will  and
      Webster, Kellie",
    booktitle = "Proceedings of the Second Workshop on Gender Bias in Natural Language Processing",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.gebnlp-1.3/",
    pages = "26--34",
    abstract = "Misrepresentation of certain communities in datasets is causing big disruptions in artificial intelligence applications. In this paper, we propose using an automatically extracted gender-balanced dataset parallel corpus from Wikipedia. This balanced set is used to perform fine-tuning techniques from a bigger model trained on unbalanced datasets to mitigate gender biases in neural machine translation."
}