Jeremy Tan

@chenqinkai would you mind sharing your code to construct the matrices? > It is not difficult to get a result, you simply need to construct three matrices, the definition of...

The test label only takes in 2 possible values: ``` test_label = torch.tensor(np.random.choice([0, 1], size=(n_stock, 1)) ,dtype=torch.int8).cuda() ``` But from the paper they have quoted that they label >+0.55% for...

`run_event.py` seems untested. Amongst other issues, the `config.num_labels` is not fixed according to the argparser but to BERT's default config. Insert the following code in `run_event.py` roughly around line 397:...