如何在 RNN 中嵌入句子序列？

Question

我正在尝试制作一个 RNN 模型（在 Pytorch 中），它需要几个句子然后将其分类为 Class 0 或 Class1.

为了这个问题，我们假设句子的max_len是4，时间步长的max_amount是5。因此，每个数据点在表格上（0是一个值用于填充填充值的那个）：

    x[1] = [
    # Input features at timestep 1
    [1, 48, 91, 0],
    # Input features at timestep 2
    [20, 5, 17, 32],
    # Input features at timestep 3
    [12, 18, 0, 0],
    # Input features at timestep 4
    [0, 0, 0, 0],
    # Input features at timestep 5
    [0, 0, 0, 0]
    ]
    y[1] = [1]

当我只有 每个目标一个句子时：我只是将每个词传递给嵌入层，然后传递给 LSTM 或 GRU ，但是当我有一个 每个目标的句子序列 时，我有点不知道该怎么办？

如何构建可以处理句子的嵌入？

Answer 1

最简单的方法是使用2种LSTM。

准备玩具数据集

xi = [
# Input features at timestep 1
[1, 48, 91, 0],
# Input features at timestep 2
[20, 5, 17, 32],
# Input features at timestep 3
[12, 18, 0, 0],
# Input features at timestep 4
[0, 0, 0, 0],
# Input features at timestep 5
[0, 0, 0, 0]
]
yi = 1

x = torch.tensor([xi, xi])
y = torch.tensor([yi, yi])

print(x.shape)
# torch.Size([2, 5, 4])

print(y.shape)
# torch.Size([2])

那么，x就是一批输入。这里 batch_size = 2.

嵌入输入

vocab_size = 1000
embed_size = 100
hidden_size = 200
embed = nn.Embedding(vocab_size, embed_size)

# shape [2, 5, 4, 100]
x = embed(x)

第一个词-LSTM是将每个序列编码成一个向量

# convert x into a batch of sequences
# Reshape into [2, 20, 100]
x = x.view(bs * 5, 4, 100)

wlstm = nn.LSTM(embed_size, hidden_size, batch_first=True)
# get the only final hidden state of each sequence

_, (hn, _) = wlstm(x)

# hn shape [1, 10, 200]

# get the output of final layer
hn = hn[0] # [10, 200]

第二个seq-LSTM是将序列编码成一个向量

# Reshape hn into [bs, num_seq, hidden_size]
hn = hn.view(2, 5, 200)

# Pass to another LSTM and get the final state hn
slstm = nn.LSTM(hidden_size, hidden_size, batch_first=True)
_, (hn, _) = slstm(hn) # [1, 2, 200]

# Similarly, get the hidden state of the last layer
hn = hn[0] # [2, 200]

添加一些分类层

pred_linear = nn.Linear(hidden_size, 1)

# [2, 1]
output = torch.sigmoid(pred_linear(hn))

如何在 RNN 中嵌入句子序列？

How to embed Sequence of Sentences in RNN?

python

neural-network

pytorch

recurrent-neural-network

embedding