This is a repository for Idiom NER and Idiom Cloze
referring to ChID: A Large-scale Chinese IDiom Dataset for Cloze Test.
-
Download ChID dataset into
data/chid
folder from hereincluding
train_data.txt
,dev_data.txt
,test_data.txt
files -
Download bert-base-chinese model into
data/bert
folder from hereincluding
config.json
,vocab.txt
,pytorch_model.bin
files
- Task One: Idiom NER
python main1.py --name NER
- Task Two: Idiom Cloze
python main2.py --name Cloze
You can modify the configuration through command line parameters or parser.py