我之前用bert做编码，再用孪生网络，效果比ESIM差不少

你好，这个词向量矩阵与vocab是否错位？ embedding_matrix[idx + 1] = model[word]#词向量矩阵，然而vocab前两位是pad 和 unk. 而词向量第一个位置为的。

请问训练的时候出现这个问题 Length of all samples has to be greater than 0, but found an element in 'lengths' that is <= 0，如何解决呀

labels 的内容是什么

想获得两个句子相似的概率，_, out_classes = output_probabilities.max(dim=1)的_是否是两个句子相似的概率

Traceback (most recent call last):
File ".\test.py", line 51, in
main("d:\test.csv", "models/best.pth.tar")
File ".\test.py", line 43, in main
model.load_state_dict(checkpoint["model"])
File "C:\Python\Python38\lib\site-packages\torch\nn\modules\module.py", line 1044, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for BertModelTest:
Missing key(s) in state_dict: "bert.bert.embeddings.position_ids".

如何解决？

I've downloaded the .tar models of ESIM and BiMPM, but I can't unzip them using any command.

您好，可以提供一个训练数据的格式案例吗，谢谢

在test.py文件中，DataLoader(test_data, shuffle=True, batch_size=batch_size) shuffle应该设为False，这是一个很低级的BUG，卡了我一天，在最意想不到的地方有BUG

Hi,I want to know how to define the train data (validation data) label?now i am define 1 means match ,and 0 means not match,but I train model ,there is a error occurs,I find maybe the label doesn't match to network output logits and probs .Thanks!

在看esim模型时，lstm 的embedding 初始化参数使用预训练的，预训练word2vec的model存在69840token，vocab.txt存在69842token,补充了2个[PAD]和[UNK]这样token,在构建预训练imbedding参数矩阵时，embedding_matrix = np.zeros((len(model.index2word) + 1, model.vector_size))，这行代码是否需要改成embedding_matrix = np.zeros((len(model.index2word) + 2, model.vector_size))，这样[PAD]和[UNK]这样token分别对应第0行和1行，与word2idx = {word: index for index, word in enumerate(vocab)}这样相对应.