Awesome

GCASeg

Code of our paper Federated Chinese Word Segmentation with Global Character Associations at ACL 2021

Citation

@inproceedings{tian-etal-2021-federated,
    title = "Federated Chinese Word Segmentation with Global Character Associations",
    author = "Tian, Yuanhe and Chen, Guimin and Qin, Han and Song, Yan",
    booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
    month = aug,
    year = "2021",
    address = "Online",
    pages = "4306--4313",
}

Training on small data

Run python run.sh to train a model on small data under data directory.