CRF代码及实现原理（二）

主要介绍CRF代码实现
 代码来源：pytorch官网
代码链接： https://pytorch.org/tutorials/beginner/nlp/advanced_tutorial.html
配合另一篇文章讲解，看此篇之前，最好看一下另一篇文章（CRF原理以及维特比解码），看完之后会很容易理解
另一篇文章链接：https://blog.csdn.net/cpluss/article/details/88824303
注意看汉语注释，完整的代码详见上面的链接

#代码的主体部分
START_TAG = "<START>"
STOP_TAG = "<STOP>"
EMBEDDING_DIM = 5
HIDDEN_DIM = 4

# 简单的训练数据
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.
        #这里是重点，model.neg_log_likelihood是主要的函数
        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!

neg_log_likelihood函数

    def neg_log_likelihood(self, sentence, tags):
        #feats是通过一个bi-lstm得到的特征，维度为（seq_length, tagset_size）,此处与crf关系不太大，因此不考虑
        #tagset_size 表示为tag的数量，例如此代码中为5
        feats = self._get_lstm_features(sentence)
        #计算得分
        forward_score = self._forward_alg(feats)
        #计算实际得分
        gold_score = self._score_sentence(feats, tags)
        #计算误差，之后有loss.backward进行训练
        return forward_score - gold_score

_forward_alg函数

    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
        #这里的forward_var就是另一篇文章中提到的不断更新的δ参数
        forward_var = init_alphas

        # Iterate through the sentence
        #这里的每一个feat,对应一个单词
        for feat in feats:
            alphas_t = []  # The forward tensors at this timestep
            #这里每一个next_tag对应一个词性，下面计算的是：
            #单词feat词性为next_tag时的得分
            for next_tag in range(self.tagset_size):
                # broadcast the emission score: it is the same regardless of
                # the previous tag
                #这个得分就是另一篇文章中提到的输入x对于y的影响的得分
                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
                #这个transition矩阵就是另一篇文章中提到t矩阵
                #transition[i][j]代表j词性转变为i词性的得分（注意前后顺序）
                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