推荐学习书目
› Learn Python the Hard Way
Python Sites
› PyPI - Python Package Index
› http://diveintopython.org/toc/index.html
› Pocoo
值得关注的项目
› PyPy
› Celery
› Jinja2
› Read the Docs
› gevent
› pyenv
› virtualenv
› Stackless Python
› Beautiful Soup
› 结巴中文分词
› Green Unicorn
› Sentry
› Shovel
› Pyflakes
› pytest
Python 编程
› pep8 Checker
Styles
› PEP 8
› Google Python Style Guide
› Code Style from The Hitchhiker's Guide
PyTorch 高级实战教程：基于 Bi-LSTM CRF 实现命名实体识别和中文分词
fendouai_com · 2019-04-12 20:05:05 +08:00 · 5035 次点击这是一个创建于 2078 天前的主题，其中的信息可能已经有所发展或是发生改变。
前言：实测 PyTorch 代码非常简洁易懂，只需要将中文分词的数据集预处理成作者提到的格式，即可很快的就迁移了这个代码到中文分词中，相关的代码后续将会分享。
具体的数据格式，这种方式并不适合处理很多的数据，但是对于 demo 来说非常友好，把英文改成中文，标签改成分词问题中的 “ BEMS ” 就可以跑起来了。
# 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()
)]
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 （我之所以提到这一点，因为与 Pytorch 和 Dynet 的工作方式类似。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，包括 Theano，Keras，TensorFlow 等。核心区别如下：
在静态工具箱中，您可以定义一次计算图，对其进行编译，然后将实例流式传输给它。 在动态工具包中，您可以为每个实例定义计算图。 它永远不会被编译并且是即时执行的。 动态工具包还有一个优点，那就是更容易调试，代码更像主机语言（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 Conditional Random Field （ Bi-LSTM CRF ） 对于本节，我们将看到用于命名实体识别的 Bi-LSTM 条件随机场的完整复杂示例。 上面的 LSTM 标记符通常足以用于词性标注，但是像 CRF 这样的序列模型对于 NER 上的强大性能非常重要。 假设熟悉 CRF。 虽然这个名字听起来很可怕，但所有模型都是 CRF，但是 LSTM 提供了特征。 这是一个高级模型，比本教程中的任何早期模型复杂得多。
实现细节： 下面的例子在 log 空间中实现了计算微分函数的正向算法，以及要解码的维特比算法。反向传播将自动为我们计算梯度。我们不必用手做任何事。
这个算法用来演示，没有优化。如果您了解正在发生的事情，您可能会很快看到，在转发算法中迭代下一个标记可能是在一个大型操作中完成的。我想用代码来提高可读性。如果你想做相关的改变，你可以用这个标记器来完成真正的任务。
# Author: Robert Guthrie
import torch
import torch.autograd as autograd
import torch.nn as nn
import torch.optim as optim
torch.manual_seed(1)
帮助程序函数，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
开始训练
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!
输出
(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])
我们没有必要在进行解码时创建计算图，因为我们不会从维特比路径得分反向传播。 因为无论如何我们都有它，尝试训练标记器，其中损失函数是维特比路径得分和测试标准路径得分之间的差异。 应该清楚的是，当预测的标签序列是正确的标签序列时，该功能是非负的和 0。 这基本上是结构感知器。
由于已经实现了 Viterbi 和 score_sentence，因此这种修改应该很短。 这是取决于训练实例的计算图形的示例。 虽然我没有尝试在静态工具包中实现它，但我想它可能但不那么直截了当。
拿起一些真实数据并进行比较！
更多 PyTorch 实战教程： http://pytorchchina.com/
 |
1
diggerdu 2019-04-12 23:12:40 +08:00 via iPhone
写的不错
|
 |
2
oblivious 2019-04-12 23:34:40 +08:00
NICE WORK!
但是有一个小问题：这好像不是中文分词，是我理解错了吗 > < |
 |
3
fendouai_com OP @oblivious 这个是 NER，可以迁移到中文分词，文章开头有提到迁移的思路。
|
Select Language