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

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 coreferenceresolution 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.
Authors (IXA members): 
Gorka Urbizu, Ander Soraluze, Olatz Arregi
Public documents: 
Publication place: 
Proceedings of the 2nd Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC 2019), co-located with NAACL 2019
ISBN edo ISSN (aldizkari, kongresu, liburu edo liburu atalak): 

Publication type:

Publication clasification: