Resources and Evaluations for Danish Entity Resolution
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Resources and Evaluations for Danish Entity Resolution. / Barrett, Maria; Lam, Hieu; Wu, Martin; Lacroix, Ophélie; Plank, Barbara; Søgaard, Anders.
Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference. Association for Computational Linguistics, 2021. s. 63-69.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Resources and Evaluations for Danish Entity Resolution
AU - Barrett, Maria
AU - Lam, Hieu
AU - Wu, Martin
AU - Lacroix, Ophélie
AU - Plank, Barbara
AU - Søgaard, Anders
PY - 2021
Y1 - 2021
N2 - Automatic coreference resolution is understudied in Danish even though most of the Danish Dependency Treebank (Buch-Kromann, 2003) is annotated with coreference relations. This paper describes a conversion of its partial, yet well-documented, coreference relations into coreference clusters and the training and evaluation of coreference models on this data. To the best of our knowledge, these are the first publicly available, neural coreference models for Danish. We also present a new entity linking annotation on the dataset using WikiData identifiers, a named entity disambiguation (NED) dataset, and a larger automatically created NED dataset enabling wikily supervised NED models. The entity linking annotation is benchmarked using a state-of-the-art neural entity disambiguation model.
AB - Automatic coreference resolution is understudied in Danish even though most of the Danish Dependency Treebank (Buch-Kromann, 2003) is annotated with coreference relations. This paper describes a conversion of its partial, yet well-documented, coreference relations into coreference clusters and the training and evaluation of coreference models on this data. To the best of our knowledge, these are the first publicly available, neural coreference models for Danish. We also present a new entity linking annotation on the dataset using WikiData identifiers, a named entity disambiguation (NED) dataset, and a larger automatically created NED dataset enabling wikily supervised NED models. The entity linking annotation is benchmarked using a state-of-the-art neural entity disambiguation model.
U2 - 10.18653/v1/2021.crac-1.7
DO - 10.18653/v1/2021.crac-1.7
M3 - Article in proceedings
SP - 63
EP - 69
BT - Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference
PB - Association for Computational Linguistics
T2 - 4th Workshop on Computational Models of Reference, Anaphora and Coreference
Y2 - 10 November 2021 through 11 November 2021
ER -
ID: 300081519