https://github.com/hiyouga/bilstm-crf-pytorch-demo
A simple baseline model for Named Entity Recognition
https://github.com/hiyouga/bilstm-crf-pytorch-demo
named-entity-recognition natural-language-processing pytorch sequence-labeling
Last synced: 4 months ago
JSON representation
A simple baseline model for Named Entity Recognition
- Host: GitHub
- URL: https://github.com/hiyouga/bilstm-crf-pytorch-demo
- Owner: hiyouga
- License: mit
- Created: 2019-11-16T09:12:53.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-11-23T09:17:34.000Z (almost 6 years ago)
- Last Synced: 2025-04-03T07:42:50.535Z (6 months ago)
- Topics: named-entity-recognition, natural-language-processing, pytorch, sequence-labeling
- Language: Python
- Size: 945 KB
- Stars: 7
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# BiLSTM-CRF-PyTorch-demo
> A simple baseline model for Named Entity Recognition.
## Requirement
- PyTorch 1.2.0
- NumPy 1.17
- Python 3.6
- GloVe pre-trained word vectors:
* Download pre-trained word vectors [here](https://github.com/stanfordnlp/GloVe#download-pre-trained-word-vectors).
* Extract the [glove.840B.300d.zip](http://nlp.stanford.edu/data/wordvecs/glove.840B.300d.zip) to the `/glove/` folder.
## Dataset
Based on the shared task of Named Entity Recognition on CoNLL 2003 (English corpus). [[link]](https://www.clips.uantwerpen.be/conll2003/ner)
## Train
```sh
python train.py
```
## Reference
- Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., & Dyer, C. "Neural Architectures for Named Entity Recognition." Proceedings of NAACL-HLT (pp. 260-270). 2016. [[pdf]](https://www.aclweb.org/anthology/N16-1030.pdf)
- Linear-chain conditional random field implemented by kmkurn: [pytorch-crf](https://github.com/kmkurn/pytorch-crf)
## License
MIT