@inproceedings{vahtola-etal-2021-coping,
    title = "Coping with Noisy Training Data Labels in Paraphrase Detection",
    author = {Vahtola, Teemu  and
      Creutz, Mathias  and
      Sj{\"o}blom, Eetu  and
      Itkonen, Sami},
    editor = "Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim  and
      Rahimi, Afshin",
    booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
    month = nov,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.wnut-1.32/",
    doi = "10.18653/v1/2021.wnut-1.32",
    pages = "291--296",
    abstract = "We present new state-of-the-art benchmarks for paraphrase detection on all six languages in the Opusparcus sentential paraphrase corpus: English, Finnish, French, German, Russian, and Swedish. We reach these baselines by fine-tuning BERT. The best results are achieved on smaller and cleaner subsets of the training sets than was observed in previous research. Additionally, we study a translation-based approach that is competitive for the languages with more limited and noisier training data."
}