@inproceedings{axelrod-etal-2019-dual,
    title = "Dual Monolingual Cross-Entropy Delta Filtering of Noisy Parallel Data",
    author = "Axelrod, Amittai  and
      Kumar, Anish  and
      Sloto, Steve",
    editor = "Bojar, Ond{\v{r}}ej  and
      Chatterjee, Rajen  and
      Federmann, Christian  and
      Fishel, Mark  and
      Graham, Yvette  and
      Haddow, Barry  and
      Huck, Matthias  and
      Yepes, Antonio Jimeno  and
      Koehn, Philipp  and
      Martins, Andr{\'e}  and
      Monz, Christof  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Post, Matt  and
      Turchi, Marco  and
      Verspoor, Karin",
    booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2)",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W19-5433/",
    doi = "10.18653/v1/W19-5433",
    pages = "245--251",
    abstract = "We introduce a purely monolingual approach to filtering for parallel data from a noisy corpus in a low-resource scenario. Our work is inspired by Junczysdowmunt:2018, but we relax the requirements to allow for cases where no parallel data is available. Our primary contribution is a dual monolingual cross-entropy delta criterion modified from Cynical data selection Axelrod:2017, and is competitive (within 1.8 BLEU) with the best bilingual filtering method when used to train SMT systems. Our approach is featherweight, and runs end-to-end on a standard laptop in three hours."
}