注意
转到末尾 下载完整的示例代码。
高级：进行动态决策和Bi-LSTM CRF#
创建日期：2017年4月8日 | 最后更新：2021年12月20日 | 最后验证：2024年11月5日
动态与静态深度学习工具包#
Pytorch 是一个*动态*神经网络工具包。动态工具包的另一个例子是 Dynet （我提到这个是因为使用 Pytorch 和 Dynet 类似。如果你在 Dynet 中看到一个例子，它可能会帮助你在 Pytorch 中实现它）。相反的是*静态*工具包，其中包括 Theano、Keras、TensorFlow 等。核心区别如下
在静态工具包中，你只需定义一次计算图，编译它，然后将实例流式传输给它。
在动态工具包中，你*为每个实例*定义一个计算图。它从不编译，而是即时执行
如果没有很多经验，很难体会到这种区别。一个例子是假设我们想构建一个深度成分解析器。假设我们的模型大致涉及以下步骤
我们自底向上构建树
标记根节点（句子的单词）
从那里，使用神经网络和单词的嵌入来找到构成成分的组合。每当形成一个新成分时，使用某种技术来获取成分的嵌入。在这种情况下，我们的网络架构将完全取决于输入句子。在句子“The green cat scratched the wall”中，在模型的某个点，我们将要组合跨度 \((i,j,r) = (1, 3, \text{NP})\)（即，一个 NP 成分从单词 1 跨越到单词 3，在这种情况下是“The green cat”）。
然而，另一个句子可能是“Somewhere, the big fat cat scratched the wall”。在这个句子中，我们将在某个时候形成成分 \((2, 4, NP)\)。我们想要形成的成分将取决于实例。如果像静态工具包那样只编译一次计算图，那么编程这种逻辑将异常困难甚至不可能。但在动态工具包中，没有只有一个预定义的计算图。每个实例都可以有一个新的计算图，因此这个问题就不存在了。
动态工具包还具有更容易调试和代码更接近宿主语言的优点（我的意思是 Pytorch 和 Dynet 看起来更像实际的 Python 代码，而不是 Keras 或 Theano）。
Bi-LSTM 条件随机场讨论#
本节我们将看到一个完整的、复杂的Bi-LSTM条件随机场（CRF）用于命名实体识别的例子。上面的LSTM标注器通常足以满足词性标注的需求，但像CRF这样的序列模型对于NER的强大性能来说是必不可少的。本文假定读者熟悉CRF。虽然这个名字听起来吓人，但所有模型都是CRF，只是LSTM提供了特征。这是一个高级模型，比本教程中任何早期模型都要复杂得多。如果你想跳过它，那没关系。要查看你是否已准备好，请检查你是否可以做到
为步骤 i 的标签 k 写出维特比变量的递推关系。
修改上述递推关系以计算前向变量。
再次修改上述递推关系以在对数空间中计算前向变量（提示：log-sum-exp）
如果你能做这三件事，你应该能够理解下面的代码。回想一下，CRF 计算条件概率。设 \(y\) 为标签序列，\(x\) 为单词的输入序列。然后我们计算
\[P(y|x) = \frac{\exp{(\text{Score}(x, y)})}{\sum_{y'} \exp{(\text{Score}(x, y')})} \]
其中分数通过定义一些对数势 \(\log \psi_i(x,y)\) 来确定，使得
\[\text{Score}(x,y) = \sum_i \log \psi_i(x,y) \]
为了使配分函数可计算，势必须只关注局部特征。
在Bi-LSTM CRF中，我们定义了两种势：发射势和转移势。索引 \(i\) 处的词的发射势来自Bi-LSTM在时间步 \(i\) 的隐藏状态。转移分数存储在一个 \(|T|x|T|\) 矩阵 \(\textbf{P}\) 中，其中 \(T\) 是标签集。在我的实现中，\(\textbf{P}_{j,k}\) 是从标签 \(k\) 转移到标签 \(j\) 的分数。所以
\[\text{Score}(x,y) = \sum_i \log \psi_\text{EMIT}(y_i \rightarrow x_i) + \log \psi_\text{TRANS}(y_{i-1} \rightarrow y_i) \]
\[= \sum_i h_i[y_i] + \textbf{P}_{y_i, y_{i-1}} \]
在这第二个表达式中，我们把标签看作被分配了唯一的非负索引。
如果以上讨论过于简短，您可以查看Michael Collins关于CRF的这篇文章。
实现注意事项#
下面的例子实现了对数空间中的前向算法来计算配分函数，以及维特比算法来解码。反向传播将自动为我们计算梯度。我们无需手动操作。
该实现并未优化。如果你理解正在发生什么，你可能会很快发现，前向算法中对下一个标签的迭代可能可以通过一个大型操作完成。我希望代码更具可读性。如果你想进行相关更改，你可能可以将此标注器用于实际任务。
# Author: Robert Guthrie
import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.optim as optim
torch.manual_seed(1)
<torch._C.Generator object at 0x7fec121506b0>
帮助函数使代码更具可读性。
def argmax(vec):
# return the argmax as a python int
_, idx = torch.max(vec, 1)
return idx.item()
def prepare_sequence(seq, to_ix):
idxs = [to_ix[w] for w in seq]
return torch.tensor(idxs, dtype=torch.long)
# Compute log sum exp in a numerically stable way for the forward algorithm
def log_sum_exp(vec):
max_score = vec[0, argmax(vec)]
max_score_broadcast = max_score.view(1, -1).expand(1, vec.size()[1])
return max_score + \
torch.log(torch.sum(torch.exp(vec - max_score_broadcast)))
创建模型
class BiLSTM_CRF(nn.Module):
def __init__(self, vocab_size, tag_to_ix, embedding_dim, hidden_dim):
super(BiLSTM_CRF, self).__init__()
self.embedding_dim = embedding_dim
self.hidden_dim = hidden_dim
self.vocab_size = vocab_size
self.tag_to_ix = tag_to_ix
self.tagset_size = len(tag_to_ix)
self.word_embeds = nn.Embedding(vocab_size, embedding_dim)
self.lstm = nn.LSTM(embedding_dim, hidden_dim // 2,
num_layers=1, bidirectional=True)
# Maps the output of the LSTM into tag space.
self.hidden2tag = nn.Linear(hidden_dim, self.tagset_size)
# Matrix of transition parameters. Entry i,j is the score of
# transitioning *to* i *from* j.
self.transitions = nn.Parameter(
torch.randn(self.tagset_size, self.tagset_size))
# These two statements enforce the constraint that we never transfer
# to the start tag and we never transfer from the stop tag
self.transitions.data[tag_to_ix[START_TAG], :] = -10000
self.transitions.data[:, tag_to_ix[STOP_TAG]] = -10000
self.hidden = self.init_hidden()
def init_hidden(self):
return (torch.randn(2, 1, self.hidden_dim // 2),
torch.randn(2, 1, self.hidden_dim // 2))
def _forward_alg(self, feats):
# Do the forward algorithm to compute the partition function
init_alphas = torch.full((1, self.tagset_size), -10000.)
# START_TAG has all of the score.
init_alphas[0][self.tag_to_ix[START_TAG]] = 0.
# Wrap in a variable so that we will get automatic backprop
forward_var = init_alphas
# Iterate through the sentence
for feat in feats:
alphas_t = [] # The forward tensors at this timestep
for next_tag in range(self.tagset_size):
# broadcast the emission score: it is the same regardless of
# the previous tag
emit_score = feat[next_tag].view(
1, -1).expand(1, self.tagset_size)
# the ith entry of trans_score is the score of transitioning to
# next_tag from i
trans_score = self.transitions[next_tag].view(1, -1)
# The ith entry of next_tag_var is the value for the
# edge (i -> next_tag) before we do log-sum-exp
next_tag_var = forward_var + trans_score + emit_score
# The forward variable for this tag is log-sum-exp of all the
# scores.
alphas_t.append(log_sum_exp(next_tag_var).view(1))
forward_var = torch.cat(alphas_t).view(1, -1)
terminal_var = forward_var + self.transitions[self.tag_to_ix[STOP_TAG]]
alpha = log_sum_exp(terminal_var)
return alpha
def _get_lstm_features(self, sentence):
self.hidden = self.init_hidden()
embeds = self.word_embeds(sentence).view(len(sentence), 1, -1)
lstm_out, self.hidden = self.lstm(embeds, self.hidden)
lstm_out = lstm_out.view(len(sentence), self.hidden_dim)
lstm_feats = self.hidden2tag(lstm_out)
return lstm_feats
def _score_sentence(self, feats, tags):
# Gives the score of a provided tag sequence
score = torch.zeros(1)
tags = torch.cat([torch.tensor([self.tag_to_ix[START_TAG]], dtype=torch.long), tags])
for i, feat in enumerate(feats):
score = score + \
self.transitions[tags[i + 1], tags[i]] + feat[tags[i + 1]]
score = score + self.transitions[self.tag_to_ix[STOP_TAG], tags[-1]]
return score
def _viterbi_decode(self, feats):
backpointers = []
# Initialize the viterbi variables in log space
init_vvars = torch.full((1, self.tagset_size), -10000.)
init_vvars[0][self.tag_to_ix[START_TAG]] = 0
# forward_var at step i holds the viterbi variables for step i-1
forward_var = init_vvars
for feat in feats:
bptrs_t = [] # holds the backpointers for this step
viterbivars_t = [] # holds the viterbi variables for this step
for next_tag in range(self.tagset_size):
# next_tag_var[i] holds the viterbi variable for tag i at the
# previous step, plus the score of transitioning
# from tag i to next_tag.
# We don't include the emission scores here because the max
# does not depend on them (we add them in below)
next_tag_var = forward_var + self.transitions[next_tag]
best_tag_id = argmax(next_tag_var)
bptrs_t.append(best_tag_id)
viterbivars_t.append(next_tag_var[0][best_tag_id].view(1))
# Now add in the emission scores, and assign forward_var to the set
# of viterbi variables we just computed
forward_var = (torch.cat(viterbivars_t) + feat).view(1, -1)
backpointers.append(bptrs_t)
# Transition to STOP_TAG
terminal_var = forward_var + self.transitions[self.tag_to_ix[STOP_TAG]]
best_tag_id = argmax(terminal_var)
path_score = terminal_var[0][best_tag_id]
# Follow the back pointers to decode the best path.
best_path = [best_tag_id]
for bptrs_t in reversed(backpointers):
best_tag_id = bptrs_t[best_tag_id]
best_path.append(best_tag_id)
# Pop off the start tag (we dont want to return that to the caller)
start = best_path.pop()
assert start == self.tag_to_ix[START_TAG] # Sanity check
best_path.reverse()
return path_score, best_path
def neg_log_likelihood(self, sentence, tags):
feats = self._get_lstm_features(sentence)
forward_score = self._forward_alg(feats)
gold_score = self._score_sentence(feats, tags)
return forward_score - gold_score
def forward(self, sentence): # dont confuse this with _forward_alg above.
# Get the emission scores from the BiLSTM
lstm_feats = self._get_lstm_features(sentence)
# Find the best path, given the features.
score, tag_seq = self._viterbi_decode(lstm_feats)
return score, tag_seq
运行训练
START_TAG = "<START>"
STOP_TAG = "<STOP>"
EMBEDDING_DIM = 5
HIDDEN_DIM = 4
# Make up some training data
training_data = [(
"the wall street journal reported today that apple corporation made money".split(),
"B I I I O O O B I O O".split()
), (
"georgia tech is a university in georgia".split(),
"B I O O O O B".split()
)]
word_to_ix = {}
for sentence, tags in training_data:
for word in sentence:
if word not in word_to_ix:
word_to_ix[word] = len(word_to_ix)
tag_to_ix = {"B": 0, "I": 1, "O": 2, START_TAG: 3, STOP_TAG: 4}
model = BiLSTM_CRF(len(word_to_ix), tag_to_ix, EMBEDDING_DIM, HIDDEN_DIM)
optimizer = optim.SGD(model.parameters(), lr=0.01, weight_decay=1e-4)
# Check predictions before training
with torch.no_grad():
precheck_sent = prepare_sequence(training_data[0][0], word_to_ix)
precheck_tags = torch.tensor([tag_to_ix[t] for t in training_data[0][1]], dtype=torch.long)
print(model(precheck_sent))
# Make sure prepare_sequence from earlier in the LSTM section is loaded
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 = torch.tensor([tag_to_ix[t] for t in tags], dtype=torch.long)
# Step 3. Run our forward pass.
loss = model.neg_log_likelihood(sentence_in, targets)
# Step 4. Compute the loss, gradients, and update the parameters by
# calling optimizer.step()
loss.backward()
optimizer.step()
# Check predictions after training
with torch.no_grad():
precheck_sent = prepare_sequence(training_data[0][0], word_to_ix)
print(model(precheck_sent))
# We got it!
(tensor(2.6907), [1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1])
(tensor(20.4906), [0, 1, 1, 1, 2, 2, 2, 0, 1, 2, 2])
练习：判别式标注的新损失函数#
在解码时，我们实际上没有必要创建计算图，因为我们不从维特比路径分数反向传播。既然我们已经有了它，尝试训练标注器，其中损失函数是维特比路径分数与金标准路径分数之间的差值。应该清楚，此函数是非负的，当预测的标签序列是正确的标签序列时为0。这本质上是*结构化感知器*。
这个修改应该很短，因为Viterbi和score_sentence已经实现。这是一个计算图形状*取决于训练实例*的例子。虽然我没有尝试在静态工具包中实现它，但我认为这是可能的，但远没有那么直接。
获取一些真实数据并进行比较！
脚本总运行时间： (0 分钟 6.919 秒)
