RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 1. Got 1 and 14 in dimension 0 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:71

[luckysunda]

In line 53, word_embedded, pretrain_embedded and lemma_embedded, these three are of different dimensions, so they clearly cannot be concatenated.

embeds = self.tanh(self.embeds2input(torch.cat((word_embedded, pretrain_embedded, lemma_embedded), 1))).view(len(sentence[0]),1,-1)
    

How to run the prediction, please help.

[LeonCrashCode]

The codes here is not updated, please refer to the codes on https://github.com/LeonCrashCode/TreeDRSparsing/tree/bs_sattn_drssup