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

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 diffe... Mehr ...

Verfasser: Poot, Corbèn
van Cranenburgh, Andreas
Dokumenttyp: contributionToPeriodical
Erscheinungsdatum: 2020
Verlag/Hrsg.: Association for Computational Linguistics (ACL)
Sprache: Englisch
Permalink: https://search.fid-benelux.de/Record/base-29443572
Datenquelle: BASE; Originalkatalog
Powered By: BASE
Link(s) : https://hdl.handle.net/11370/33f9913e-2c3d-43a0-be45-dcc3a9f62975

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