@inproceedings{bhartiya-etal-2022-dis,
    title = "{D}i{S}-{R}e{X}: A Multilingual Dataset for Distantly Supervised Relation Extraction",
    author = "Bhartiya, Abhyuday  and
      Badola, Kartikeya  and
      Mausam",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.acl-short.95/",
    doi = "10.18653/v1/2022.acl-short.95",
    pages = "849--863",
    abstract = {Our goal is to study the novel task of distant supervision for multilingual relation extraction (Multi DS-RE). Research in Multi DS-RE has remained limited due to the absence of a reliable benchmarking dataset. The only available dataset for this task, RELX-Distant (K{\"o}ksal and {\"O}zg{\"u}r, 2020), displays several unrealistic characteristics, leading to a systematic overestimation of model performance. To alleviate these concerns, we release a new benchmark dataset for the task, named DiS-ReX. We also modify the widely-used bag attention models using an mBERT encoder and provide the first baseline results on the proposed task. We show that DiS-ReX serves as a more challenging dataset than RELX-Distant, leaving ample room for future research in this domain.}
}