@inproceedings{van-cranenburgh-etal-2026-golemcoref,
    title = "{GOLEM}coref: A Multilingual Coreference Dataset of Fiction",
    author = "Van Cranenburgh, Andreas  and
      Yang, Xiaoyan  and
      Alvanita  and
      Di Domenico, Cecilia Nicole  and
      Ferragud, Maria  and
      Graciotti, Arianna  and
      Kim, Byungjun  and
      Park, Seonyeong  and
      Solissa, Noa Visser  and
      Zhou, Xiaoyu  and
      Pianzola, Federico",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-short.39/",
    pages = "472--480",
    ISBN = "979-8-89176-391-3",
    abstract = "We present a multilingual coreference dataset of 827k tokens of fiction in 7 languages: Bahasa Indonesia, Chinese, Dutch, English, Italian, Korean, and Spanish. The dataset includes full stories of diverse lengths, ranging from 500 to 17k words. We discuss our annotation scheme focusing on characters and language-specific challenges we encountered. Finally we present evaluation results of a neural coreference system trained on our dataset. We show that jointly training a system across all languages provides a strong improvement over monolingually trained models. The dataset is available under a creative commons license in CoNLL-2012 and CorefUD format at https://github.com/GOLEM-lab/GOLEMcoref/"
}