@inproceedings{agrawal-carpuat-2020-generating,
    title = "Generating Diverse Translations via Weighted Fine-tuning and Hypotheses Filtering for the {D}uolingo {STAPLE} Task",
    author = "Agrawal, Sweta  and
      Carpuat, Marine",
    editor = "Birch, Alexandra  and
      Finch, Andrew  and
      Hayashi, Hiroaki  and
      Heafield, Kenneth  and
      Junczys-Dowmunt, Marcin  and
      Konstas, Ioannis  and
      Li, Xian  and
      Neubig, Graham  and
      Oda, Yusuke",
    booktitle = "Proceedings of the Fourth Workshop on Neural Generation and Translation",
    month = jul,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.ngt-1.21/",
    doi = "10.18653/v1/2020.ngt-1.21",
    pages = "178--187",
    abstract = "This paper describes the University of Maryland`s submission to the Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE). Unlike the standard machine translation task, STAPLE requires generating a set of outputs for a given input sequence, aiming to cover the space of translations produced by language learners. We adapt neural machine translation models to this requirement by (a) generating n-best translation hypotheses from a model fine-tuned on learner translations, oversampled to reflect the distribution of learner responses, and (b) filtering hypotheses using a feature-rich binary classifier that directly optimizes a close approximation of the official evaluation metric. Combination of systems that use these two strategies achieves F1 scores of 53.9{\%} and 52.5{\%} on Vietnamese and Portuguese, respectively ranking 2nd and 4th on the leaderboard."
}