BiLSTM-LAN
BiLSTM-LAN copied to clipboard
inference
Ask a question:How to do in prediction, which don't have label? Thanks.
X^l represents all candidates' label embeddings. During training, the model does not utilize gold information in X^l, the only supervision is on the last layer's attention weights.
ok, Thanks!
@oldstree Hi, I am also trying to use the tool. But I am wondering where the dataset is. I saw you run this model and posted issues. What dataset did you use? Could you please share with me?