Running Steps

1.download data from https://www.heywhale.com/org/gaiic2022/competition/area/620b34ed28270b0017b823ad/content/2

2.download tencent word vectors from https://ai.tencent.com/ailab/nlp/en/download.html, and put it in user_data/w2v_model

3.run src/w2v/build_w2v_vocab.py

4.run src/utils/process_data.py

5.run src/utils/build_label_vocab.py

6.run_ner_lebert.py

If you like it, you can star it !

Paper Address : https://arxiv.org/pdf/2105.07148v3.pdf