@inproceedings{fenogenova-etal-2020-read,
    title = "Read and Reason with {M}u{S}e{RC} and {R}u{C}o{S}: Datasets for Machine Reading Comprehension for {R}ussian",
    author = "Fenogenova, Alena  and
      Mikhailov, Vladislav  and
      Shevelev, Denis",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.coling-main.570/",
    doi = "10.18653/v1/2020.coling-main.570",
    pages = "6481--6497",
    abstract = "The paper introduces two Russian machine reading comprehension (MRC) datasets, called MuSeRC and RuCoS, which require reasoning over multiple sentences and commonsense knowledge to infer the answer. The former follows the design of MultiRC, while the latter is a counterpart of the ReCoRD dataset. The datasets are included in RussianSuperGLUE, the Russian general language understanding benchmark. We provide a comparative analysis and demonstrate that the proposed tasks are relatively more complex as compared to the original ones for English. Besides, performance results of human solvers and BERT-based models show that MuSeRC and RuCoS represent a challenge for recent advanced neural models. We thus hope to facilitate research in the field of MRC for Russian and prompt the study of multi-hop reasoning in a cross-lingual scenario."
}