Results
3
comments of
cairo
Probably the criterion loss function is the problem. ```python # shape [10, 2], not very accurate output out = torch.tensor([[ -8.4014, -0.0002], [-10.3151, -0.0000], [ -8.8440, -0.0001], [ -7.5148, -0.0005],...
> Start Training to logic_form [pointer-network] 你好，script中的train_pn和test_pn分别是使用复现的pointer network进行logical form的训练和生成。
WebAsKB这个目录下是生成ptrNet所需数据的代码，代码来源于： https://github.com/alontalmor/WebAsKB