注意
点击 这里 下载完整的示例代码
序列模型和长短期记忆网络¶
到目前为止，我们已经看到了各种前馈网络。也就是说，网络根本不维护任何状态。这可能不是我们想要的行为。序列模型是 NLP 的核心：它们是模型，其中输入之间存在某种时间上的依赖关系。序列模型的经典示例是用于词性标注的隐马尔可夫模型。另一个示例是条件随机场。
循环神经网络是一种维护某种状态的网络。例如，它的输出可以用作下一个输入的一部分，以便信息可以在网络遍历序列时传播。在 LSTM 的情况下，对于序列中的每个元素，都有一个对应的隐藏状态 \(h_t\)，它原则上可以包含来自序列中任意早期的信息。我们可以使用隐藏状态来预测语言模型中的单词、词性标记以及无数其他事物。
Pytorch 中的 LSTM¶
在进入示例之前，请注意以下几点。Pytorch 的 LSTM 期望所有输入都是 3 维张量。这些张量的轴的语义很重要。第一个轴是序列本身，第二个轴索引小批量中的实例，第三个轴索引输入的元素。我们还没有讨论小批量处理，所以让我们忽略它，并假设我们始终在第二个轴上只有 1 个维度。如果我们想对句子“The cow jumped”运行序列模型，我们的输入应该如下所示：
但请记住，还有一个额外的第二维，大小为 1。
此外，您可以一次遍历一个序列，在这种情况下，第一个轴的大小也为 1。
让我们看一个简单的示例。
# Author: Robert Guthrie
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
torch.manual_seed(1)
<torch._C.Generator object at 0x7fa75abf3950>
lstm = nn.LSTM(3, 3) # Input dim is 3, output dim is 3
inputs = [torch.randn(1, 3) for _ in range(5)] # make a sequence of length 5
# initialize the hidden state.
hidden = (torch.randn(1, 1, 3),
torch.randn(1, 1, 3))
for i in inputs:
# Step through the sequence one element at a time.
# after each step, hidden contains the hidden state.
out, hidden = lstm(i.view(1, 1, -1), hidden)
# alternatively, we can do the entire sequence all at once.
# the first value returned by LSTM is all of the hidden states throughout
# the sequence. the second is just the most recent hidden state
# (compare the last slice of "out" with "hidden" below, they are the same)
# The reason for this is that:
# "out" will give you access to all hidden states in the sequence
# "hidden" will allow you to continue the sequence and backpropagate,
# by passing it as an argument to the lstm at a later time
# Add the extra 2nd dimension
inputs = torch.cat(inputs).view(len(inputs), 1, -1)
hidden = (torch.randn(1, 1, 3), torch.randn(1, 1, 3)) # clean out hidden state
out, hidden = lstm(inputs, hidden)
print(out)
print(hidden)
tensor([[[-0.0187, 0.1713, -0.2944]],
[[-0.3521, 0.1026, -0.2971]],
[[-0.3191, 0.0781, -0.1957]],
[[-0.1634, 0.0941, -0.1637]],
[[-0.3368, 0.0959, -0.0538]]], grad_fn=<MkldnnRnnLayerBackward0>)
(tensor([[[-0.3368, 0.0959, -0.0538]]], grad_fn=<StackBackward0>), tensor([[[-0.9825, 0.4715, -0.0633]]], grad_fn=<StackBackward0>))
示例：用于词性标注的 LSTM¶
在本节中，我们将使用 LSTM 来获取词性标签。我们不会使用 Viterbi 或 Forward-Backward 或类似的东西，但作为一项（具有挑战性的）练习，请读者思考在您了解了正在发生的事情之后如何使用 Viterbi。在本例中，我们还提到了嵌入。如果您不熟悉嵌入，您可以在 此处 阅读有关嵌入的更多信息。
模型如下：令我们的输入句子为 \(w_1, \dots, w_M\)，其中 \(w_i \in V\)，我们的词汇。另外，令 \(T\) 为我们的标签集，\(y_i\) 为词 \(w_i\) 的标签。用 \(\hat{y}_i\) 表示我们对词 \(w_i\) 的标签的预测。
这是一个结构预测模型，我们的输出是一个序列 \(\hat{y}_1, \dots, \hat{y}_M\)，其中 \(\hat{y}_i \in T\)。
要进行预测，请在句子上传递一个 LSTM。将时间步 \(i\) 处的隐藏状态表示为 \(h_i\)。另外，为每个标签分配一个唯一的索引（就像我们在词嵌入部分中拥有 word_to_ix 一样）。然后，我们对 \(\hat{y}_i\) 的预测规则为：
也就是说，取隐藏状态的仿射映射的对数 softmax，预测的标签是该向量中具有最大值的标签。注意，这立即意味着 \(A\) 的目标空间的维数为 \(|T|\)。
准备数据
def prepare_sequence(seq, to_ix):
idxs = [to_ix[w] for w in seq]
return torch.tensor(idxs, dtype=torch.long)
training_data = [
# Tags are: DET - determiner; NN - noun; V - verb
# For example, the word "The" is a determiner
("The dog ate the apple".split(), ["DET", "NN", "V", "DET", "NN"]),
("Everybody read that book".split(), ["NN", "V", "DET", "NN"])
]
word_to_ix = {}
# For each words-list (sentence) and tags-list in each tuple of training_data
for sent, tags in training_data:
for word in sent:
if word not in word_to_ix: # word has not been assigned an index yet
word_to_ix[word] = len(word_to_ix) # Assign each word with a unique index
print(word_to_ix)
tag_to_ix = {"DET": 0, "NN": 1, "V": 2} # Assign each tag with a unique index
# These will usually be more like 32 or 64 dimensional.
# We will keep them small, so we can see how the weights change as we train.
EMBEDDING_DIM = 6
HIDDEN_DIM = 6
{'The': 0, 'dog': 1, 'ate': 2, 'the': 3, 'apple': 4, 'Everybody': 5, 'read': 6, 'that': 7, 'book': 8}
创建模型
class LSTMTagger(nn.Module):
def __init__(self, embedding_dim, hidden_dim, vocab_size, tagset_size):
super(LSTMTagger, self).__init__()
self.hidden_dim = hidden_dim
self.word_embeddings = nn.Embedding(vocab_size, embedding_dim)
# The LSTM takes word embeddings as inputs, and outputs hidden states
# with dimensionality hidden_dim.
self.lstm = nn.LSTM(embedding_dim, hidden_dim)
# The linear layer that maps from hidden state space to tag space
self.hidden2tag = nn.Linear(hidden_dim, tagset_size)
def forward(self, sentence):
embeds = self.word_embeddings(sentence)
lstm_out, _ = self.lstm(embeds.view(len(sentence), 1, -1))
tag_space = self.hidden2tag(lstm_out.view(len(sentence), -1))
tag_scores = F.log_softmax(tag_space, dim=1)
return tag_scores
训练模型
model = LSTMTagger(EMBEDDING_DIM, HIDDEN_DIM, len(word_to_ix), len(tag_to_ix))
loss_function = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.1)
# See what the scores are before training
# Note that element i,j of the output is the score for tag j for word i.
# Here we don't need to train, so the code is wrapped in torch.no_grad()
with torch.no_grad():
inputs = prepare_sequence(training_data[0][0], word_to_ix)
tag_scores = model(inputs)
print(tag_scores)
for epoch in range(300): # again, normally you would NOT do 300 epochs, it is toy data
for sentence, tags in training_data:
# Step 1. Remember that Pytorch accumulates gradients.
# We need to clear them out before each instance
model.zero_grad()
# Step 2. Get our inputs ready for the network, that is, turn them into
# Tensors of word indices.
sentence_in = prepare_sequence(sentence, word_to_ix)
targets = prepare_sequence(tags, tag_to_ix)
# Step 3. Run our forward pass.
tag_scores = model(sentence_in)
# Step 4. Compute the loss, gradients, and update the parameters by
# calling optimizer.step()
loss = loss_function(tag_scores, targets)
loss.backward()
optimizer.step()
# See what the scores are after training
with torch.no_grad():
inputs = prepare_sequence(training_data[0][0], word_to_ix)
tag_scores = model(inputs)
# The sentence is "the dog ate the apple". i,j corresponds to score for tag j
# for word i. The predicted tag is the maximum scoring tag.
# Here, we can see the predicted sequence below is 0 1 2 0 1
# since 0 is index of the maximum value of row 1,
# 1 is the index of maximum value of row 2, etc.
# Which is DET NOUN VERB DET NOUN, the correct sequence!
print(tag_scores)
tensor([[-1.1389, -1.2024, -0.9693],
[-1.1065, -1.2200, -0.9834],
[-1.1286, -1.2093, -0.9726],
[-1.1190, -1.1960, -0.9916],
[-1.0137, -1.2642, -1.0366]])
tensor([[-0.0462, -4.0106, -3.6096],
[-4.8205, -0.0286, -3.9045],
[-3.7876, -4.1355, -0.0394],
[-0.0185, -4.7874, -4.6013],
[-5.7881, -0.0186, -4.1778]])
练习：使用字符级特征增强 LSTM 词性标注器¶
在上面的示例中，每个词都有一个嵌入，用作我们序列模型的输入。让我们用从词的字符派生的表示来增强词嵌入。我们预计这将有很大帮助，因为字符级信息（如词缀）对词性有很大影响。例如，带有词缀-ly的词在英语中几乎总是被标记为副词。
为此，令 \(c_w\) 为词 \(w\) 的字符级表示。令 \(x_w\) 为词嵌入，如前所述。然后，我们序列模型的输入是 \(x_w\) 和 \(c_w\) 的串联。因此，如果 \(x_w\) 的维数为 5，\(c_w\) 的维数为 3，则我们的 LSTM 应该接受维数为 8 的输入。
要获得字符级表示，请在词的字符上执行 LSTM，并令 \(c_w\) 为该 LSTM 的最终隐藏状态。提示
您的新模型中将有两个 LSTM。第一个 LSTM 输出 POS 标签得分，第二个 LSTM 输出每个词的字符级表示。
要对字符执行序列模型，您将必须嵌入字符。字符嵌入将作为字符 LSTM 的输入。
脚本的总运行时间：（0 分钟 0.849 秒）
