@inproceedings{bawden-etal-2020-parbleu,
    title = "{P}ar{BLEU}: Augmenting Metrics with Automatic Paraphrases for the {WMT}`20 Metrics Shared Task",
    author = {Bawden, Rachel  and
      Zhang, Biao  and
      T{\"a}ttar, Andre  and
      Post, Matt},
    editor = {Barrault, Lo{\"i}c  and
      Bojar, Ond{\v{r}}ej  and
      Bougares, Fethi  and
      Chatterjee, Rajen  and
      Costa-juss{\`a}, Marta R.  and
      Federmann, Christian  and
      Fishel, Mark  and
      Fraser, Alexander  and
      Graham, Yvette  and
      Guzman, Paco  and
      Haddow, Barry  and
      Huck, Matthias  and
      Yepes, Antonio Jimeno  and
      Koehn, Philipp  and
      Martins, Andr{\'e}  and
      Morishita, Makoto  and
      Monz, Christof  and
      Nagata, Masaaki  and
      Nakazawa, Toshiaki  and
      Negri, Matteo},
    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.wmt-1.98/",
    pages = "887--894",
    abstract = "We describe parBLEU, parCHRF++, and parESIM, which augment baseline metrics with automatically generated paraphrases produced by PRISM (Thompson and Post, 2020a), a multilingual neural machine translation system. We build on recent work studying how to improve BLEU by using diverse automatically paraphrased references (Bawden et al., 2020), extending experiments to the multilingual setting for the WMT2020 metrics shared task and for three base metrics. We compare their capacity to exploit up to 100 additional synthetic references. We find that gains are possible when using additional, automatically paraphrased references, although they are not systematic. However, segment-level correlations, particularly into English, are improved for all three metrics and even with higher numbers of paraphrased references."
}