lonePatient/BERT-NER-Pytorch
Chinese NER system using BERT models with Softmax, CRF, and Span-based decoding layers.
Not currently ranked — collecting fresh signals.
star history
This repository implements named entity recognition for Chinese text using BERT and ALBERT pre-trained models. It provides three decoding approaches: Softmax classification, conditional random field (CRF) layers, and span-based extraction. The project supports adversarial training, focal loss, and label smoothing for improved performance. It evaluates on CLUENER and CNER datasets with benchmark F1 scores around 0.81 for BERT+Span.
Frequently asked
- What is lonePatient/BERT-NER-Pytorch?
- Chinese NER system using BERT models with Softmax, CRF, and Span-based decoding layers.
- Is BERT-NER-Pytorch open source?
- Yes — lonePatient/BERT-NER-Pytorch is open source, released under the MIT license.
- What language is BERT-NER-Pytorch written in?
- lonePatient/BERT-NER-Pytorch is primarily written in Python.
- How popular is BERT-NER-Pytorch?
- lonePatient/BERT-NER-Pytorch has 2.2k stars on GitHub.
- Where can I find BERT-NER-Pytorch?
- lonePatient/BERT-NER-Pytorch is on GitHub at https://github.com/lonePatient/BERT-NER-Pytorch.