Unsupervised cross-lingual model transfer for named entity recognition with contextualized word representations.
Named entity recognition (NER) is one fundamental task in the natural language processing (NLP) community. Supervised neural network models based on contextualized word representations can achieve highly-competitive performance, which requires a large-scale manually-annotated corpus for training. Wh...
Enregistré dans:
Auteurs principaux: | Huijiong Yan, Tao Qian, Liang Xie, Shanguang Chen |
---|---|
Format: | article |
Langue: | EN |
Publié: |
Public Library of Science (PLoS)
2021
|
Sujets: | |
Accès en ligne: | https://doaj.org/article/7f90d99991f446ffb3c4044a3dca981b |
Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
Documents similaires
-
Enhancing unsupervised medical entity linking with multi-instance learning
par: Cheng Yan, et autres
Publié: (2021) -
Enhancing Korean Named Entity Recognition With Linguistic Tokenization Strategies
par: Gyeongmin Kim, et autres
Publié: (2021) -
Named Entity Recognition of Enterprise Annual Report Integrated with BERT
par: ZHANG Jingyi, et autres
Publié: (2021) -
GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
par: Qinjun Qiu, et autres
Publié: (2019) -
Video Scene Information Detection Based on Entity Recognition
par: Hui Qian, et autres
Publié: (2021)