weihuan xia

Results 3 issues of weihuan xia

在asgcn.py代码里面,位置权重的分母为什么是context_len而不是text_len,论文中分母是n是句子总长度呀?有点疑惑,希望作者解答,感谢

如果我用BERT预训练做ASGCN,aspect_double_idx修改成aspect_double_idx = torch.cat([left_len.unsqueeze(1), (left_len+aspect_len-1).unsqueeze(1)], dim=1)是正确的嘛,我按照上述修改会报错。 File "/root/autodl-tmp/ABSA-PyTorch-master/models/asgcn_bert.py", line 75, in mask mask = torch.tensor(mask, dtype=torch.float).unsqueeze(2).to(self.opt.device) ValueError: expected sequence of length 85 at dim 1 (got 90)

Hello, what's the difference with senticNet20, 30, 40 ...