Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque

Gorka Urbizu, Ander Soraluze, Olatz Arregi


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.
Anthology ID:
W19-2806
Volume:
Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference
Month:
June
Year:
2019
Address:
Minneapolis, USA
Editors:
Maciej Ogrodniczuk, Sameer Pradhan, Yulia Grishina, Vincent Ng
Venue:
CRAC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
35–41
Language:
URL:
https://aclanthology.org/W19-2806
DOI:
10.18653/v1/W19-2806
Bibkey:
Cite (ACL):
Gorka Urbizu, Ander Soraluze, and Olatz Arregi. 2019. Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque. In Proceedings of the Second Workshop on Computational Models of Reference, Anaphora and Coreference, pages 35–41, Minneapolis, USA. Association for Computational Linguistics.
Cite (Informal):
Deep Cross-Lingual Coreference Resolution for Less-Resourced Languages: The Case of Basque (Urbizu et al., CRAC 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/W19-2806.pdf