A Benchmark of Rule-Based and Neural Coreference Resolution in Dutch Novels and News

    OnderzoeksoutputAcademicpeer review

    18 Downloads (Pure)

    Samenvatting

    We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text. The results provide insight into the relative strengths of data-driven and knowledge-driven systems, as well as the influence of domain, document length, and annotation schemes. The neural system performs best on news/Wikipedia text, while the rule-based system performs best on literature. The neural system shows weaknesses with limited training data and long documents, while the rule-based system is affected by annotation differences. The code and models used in this paper are available at https://github.com/andreasvc/crac2020
    Originele taal-2English
    TitelProceedings of the Third Workshop on Computational Models of Reference, Anaphora and Coreference
    RedacteurenMaciej Ogrodniczuk, Vincent Ng, Yulia Grishina, Sameer Pradhan
    UitgeverijAssociation for Computational Linguistics (ACL)
    Pagina's79-90
    Aantal pagina's12
    StatusPublished - 2020
    EvenementWorkshop on Computational Models of Reference, Anaphora and Coreference - Online
    Duur: 12-dec-2020 → …
    Congresnummer: 3

    Workshop

    WorkshopWorkshop on Computational Models of Reference, Anaphora and Coreference
    Periode12/12/2020 → …

    Citeer dit