Contextualized Word Representations from Distant Supervision with and for NER

TitreContextualized Word Representations from Distant Supervision with and for NER
Type de publicationConference Paper
Année de publication2019
AuteursGhaddar, A., and P. Langlais
Nom de la conférenceProceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
ÉditeurAssociation for Computational Linguistics
Endroit d'éditionHong Kong, China
RésuméWe describe a special type of deep contextualized word representation that is learned from distant supervision annotations and dedicated to named entity recognition. Our extensive experiments on 7 datasets show systematic gains across all domains over strong baselines, and demonstrate that our representation is complementary to previously proposed embeddings. We report new state-of-the-art results on CONLL and ONTONOTES datasets.
URLhttps://www.aclweb.org/anthology/D19-5513
DOI10.18653/v1/D19-5513