An entity-targeted active learning strategy, combined with cross-lingual transfer and partial-CRF training, outperforms sequence-level and random baselines for low-resource NER.
Mortensen, and Jaime Carbonell
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Little Annotation does a Lot of Good: A Study in Bootstrapping Low-resource Named Entity Recognizers
An entity-targeted active learning strategy, combined with cross-lingual transfer and partial-CRF training, outperforms sequence-level and random baselines for low-resource NER.