Low-resource named entity recognition via multi-source projection: Not quite there yet?
Jan Vium Enghoff, Søren Harrison, Żeljko Agić · 2018
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.