@inproceedings{urbizu-etal-2019-deep,
    title = "Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of {B}asque",
    author = "Urbizu, Gorka  and
      Soraluze, Ander  and
      Arregi, Olatz",
    editor = "Ogrodniczuk, Maciej  and
      Pradhan, Sameer  and
      Grishina, Yulia  and
      Ng, Vincent",
    booktitle = "Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference",
    month = jun,
    year = "2019",
    address = "Minneapolis, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W19-2806/",
    doi = "10.18653/v1/W19-2806",
    pages = "35--41",
    abstract = "In this paper, we present a cross-lingual neural coreference resolution system for a less-resourced language such as Basque. To begin with, we build the first neural coreference resolution system for Basque, training it with the relatively small EPEC-KORREF corpus (45,000 words). Next, a cross-lingual coreference resolution system is designed. With this approach, the system learns from a bigger English corpus, using cross-lingual embeddings, to perform the coreference resolution for Basque. The cross-lingual system obtains slightly better results (40.93 F1 CoNLL) than the monolingual system (39.12 F1 CoNLL), without using any Basque language corpus to train it."
}