Low-resource named entity recognition via multi-source projection: Not quite there yet? (CROSBI ID 666225)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Enghoff, Jan Vium ; Harrison, Søren ; Agić, Željko
engleski
Low-resource named entity recognition via multi-source projection: Not quite there yet?
Projecting linguistic annotations through word alignments is one of the most prevalent approaches to cross-lingual transfer learning. Conventional wisdom suggests that annotation projection “just works” regardless of the task at hand. We carefully consider multi-source projection for named entity recognition. Our experiment with 17 languages shows that to detect named entities in true low-resource languages, annotation projection may not be the right way to move forward. On a more positive note, we also uncover the conditions that do favor named entity projection from multiple sources. We argue these are infeasible under noisy low-resource constraints.
named entity recognition ; low-resource languages ; annotation projection
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
195-201.
2018.
objavljeno
Podaci o matičnoj publikaciji
W-NUT 2018: The 4th Workshop on Noisy User-generated Text: Proceedings of the Workshop
Xu, Wei ; Ritter, Alan ; Baldwin, Tim ; Rahimi, Afshin
Brisel: Association for Computational Linguistics (ACL)
978-1-948087-79-7
Podaci o skupu
4th Workshop on Noisy User-generated Text (W-NUT 2018)
predavanje
01.11.2018-01.11.2018
Bruxelles, Belgija