gkaramanolakis / CLTS

Cross-lingual Transfer of Weak Supervision (EMNLP Findings 2020)
Apache License 2.0
7 stars 1 forks source link

BaseException: Unknown dataset: cls_books #1

Open TranBinhLuatUIT opened 3 years ago

TranBinhLuatUIT commented 3 years ago

I follow your guide and encounter an error:

File "/content/drive/My Drive/NER/CLTS/clts/Cotraining.py", line 213, in cotrain_wrapper train_tokenizer(dataset, train_size=train_size, savepath=vocab_path) File "/content/drive/My Drive/NER/CLTS/clts/Tokenizer.py", line 169, in train_tokenizer raise(BaseException('Unknown dataset: {}'.format(dataset))) BaseException: Unknown dataset: cls_books

I checked the dataset variable again and it still is "cls". Can you help me with what am I doing wrong :( Thanks

ahtamjan commented 3 years ago

same mistake