@inproceedings{rybak-2023-maupqa,
    title = "{MAUPQA}: Massive Automatically-created {P}olish Question Answering Dataset",
    author = "Rybak, Piotr",
    editor = "Piskorski, Jakub  and
      Marci{\'n}czuk, Micha{\l}  and
      Nakov, Preslav  and
      Ogrodniczuk, Maciej  and
      Pollak, Senja  and
      P{\v{r}}ib{\'a}{\v{n}}, Pavel  and
      Rybak, Piotr  and
      Steinberger, Josef  and
      Yangarber, Roman",
    booktitle = "Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023)",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.bsnlp-1.2/",
    doi = "10.18653/v1/2023.bsnlp-1.2",
    pages = "11--16",
    abstract = "Recently, open-domain question answering systems have begun to rely heavily on annotated datasets to train neural passage retrievers. However, manually annotating such datasets is both difficult and time-consuming, which limits their availability for less popular languages. In this work, we experiment with several methods for automatically collecting weakly labeled datasets and show how they affect the performance of the neural passage retrieval models. As a result of our work, we publish the MAUPQA dataset, consisting of nearly 400,000 question-passage pairs for Polish, as well as the HerBERT-QA neural retriever."
}