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...
Saved in:
Main Authors: | Huijiong Yan, Tao Qian, Liang Xie, Shanguang Chen |
---|---|
Format: | article |
Language: | EN |
Published: |
Public Library of Science (PLoS)
2021
|
Subjects: | |
Online Access: | https://doaj.org/article/7f90d99991f446ffb3c4044a3dca981b |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Enhancing unsupervised medical entity linking with multi-instance learning
by: Cheng Yan, et al.
Published: (2021) -
Enhancing Korean Named Entity Recognition With Linguistic Tokenization Strategies
by: Gyeongmin Kim, et al.
Published: (2021) -
Named Entity Recognition of Enterprise Annual Report Integrated with BERT
by: ZHANG Jingyi, et al.
Published: (2021) -
GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
by: Qinjun Qiu, et al.
Published: (2019) -
Video Scene Information Detection Based on Entity Recognition
by: Hui Qian, et al.
Published: (2021)