Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection
Domaine:
natural language processingType de record:
paper
Créateur:
FanCoh
Hôte:
Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly. In this paper, we introduce a novel approach to sequence tagging that learns to correct the errors from cross-lingual projection using an explicit debiasing layer. This is framed as joint learning over two corpora, one tagged with gold standard and the other with projected tags. We evaluated with only 1,000 tokens tagged with gold standard tags, along with more plentiful parallel data. Our system equals or exceeds the state-of-the-art on eight simulated low-resource settings, as well as two real low-resource languages, Malagasy and Kinyarwanda.
Similaires
dhgarrette/low-resource-pos-tagging-2013Cross-lingual NER Generalization Errors Across Typologically Distant Low-Resource LanguagesANEA: Distant Supervision for Low-Resource Named Entity RecognitionCross-lingual NER Annotation Projection vs. Zero-Shot Few-Shot Learning in Low-Resource LanguagesPart-of-Speech (POS) Tagging of Low-Resource Language (Limbu) with Deep learningImproving Amazigh POS tagging using machine learning