Yue Yu

Thanks for pointing this out! Actually, we don't use semeval dataset, so this object is not used.

Hi Chiyu, To adapt COSINE for semi-supervised learning, I suggest you first train your model with clean labels (the same as the 'init' step in the paper), then use self-training...

Hi Chiyu, Yes, you need to save the pre-trained model training on clean data, which serves as the initialization for self-training. For unlabeled data, here we keep the labels to...

Hi, For parameter setting, since COSINE is not mainly designed for semi-supervised learning, I haven't tuned the hyperparameters carefully. Overall, I believe the learning rate for fine-tuning can be searched...

Hi, here I recommend you to first tune the T1 to get a good initialization (which should be around 65% as reported in the paper), then with a good initialization,...

Thanks for the suggestion! We have updated these packages.

We train the entity embeddings based on the code in https://github.com/thunlp/OpenKE.