Kaiyinzhou
Kaiyinzhou
@GhadaAlfattni If you want to use your own model, first you must make sure that the parameter format of the model is the same as that provided by BERT official,...
@zanderbush Sorry, Google Colab is not convenient for my network.
该数据集下载时签署了相应协议，不可随意传播。。这是数据网址。https://biendata.com/competition/CCKS2018_1/leaderboard/
Yes, no problem was found when i applied it on some different data,. Maybe you should check the codes.
I think this problem may caused by different languages. For german, you should download German-based model that released by google.
@songtaoshi Yes, you are right, I updated the script to write the test results to result files. This way we can use the official script to evaluate. If I am...
I've not used this corpus before, can you give out the link.
Recently, I've been busy with other work. So, it's hard for me to finished this integration. When I finish the work at hand, i will try it.
@hyli666 Thank your . you are right, its necessary to do masking, if not the total loss will be influenced and the calculation speed will drop. But i think such...