文章目录
- [条件随机场(Conditional Random Field, CRF)](#条件随机场(Conditional Random Field, CRF))
- 效果展示
序列标注指给定输入序列，给序列中每个Token进行标注标签的过程。序列标注问题通常用于从文本中进行信息抽取，包括分词(Word Segmentation)、词性标注(Position Tagging)、命名实体识别(Named Entity Recognition, NER)等。
常见的实体标识的方法有BMES标注法（四位序列标注法）、BIO标注法（三位序列标注法）、BIOES标注法（四位序列标注法），这里使用了一种常见的命名实体识别的标注方法------"BIOE"标注，将一个实体(Entity)的开头标注为B，其他部分标注为I，非实体标注为O。
条件随机场(Conditional Random Field, CRF)
考虑到序列标注问题的线性序列特点，本节所述的条件随机场特指线性链条件随机场(Linear Chain CRF)
score计算
首先根据公式 (3)
计算正确标签序列所对应的得分，这里需要注意，除了转移概率矩阵 𝐏外，还需要维护两个大小为 |𝑇|的向量，分别作为序列开始和结束时的转移概率。同时我们引入了一个掩码矩阵 𝑚𝑎𝑠𝑘，将多个序列打包为一个Batch时填充的值忽略，使得 Score计算仅包含有效的Token。
python
def compute_score(emissions, tags, seq_ends, mask, trans, start_trans, end_trans):
# emissions: (seq_length, batch_size, num_tags)
# tags: (seq_length, batch_size)
# mask: (seq_length, batch_size)
seq_length, batch_size = tags.shape
mask = mask.astype(emissions.dtype)
# 将score设置为初始转移概率
# shape: (batch_size,)
score = start_trans[tags[0]]
# score += 第一次发射概率
# shape: (batch_size,)
score += emissions[0, mnp.arange(batch_size), tags[0]]
for i in range(1, seq_length):
# 标签由i-1转移至i的转移概率（当mask == 1时有效）
# shape: (batch_size,)
score += trans[tags[i - 1], tags[i]] * mask[i]
# 预测tags[i]的发射概率（当mask == 1时有效）
# shape: (batch_size,)
score += emissions[i, mnp.arange(batch_size), tags[i]] * mask[i]
# 结束转移
# shape: (batch_size,)
last_tags = tags[seq_ends, mnp.arange(batch_size)]
# score += 结束转移概率
# shape: (batch_size,)
score += end_trans[last_tags]
return scoreNormalizer计算
python
def compute_normalizer(emissions, mask, trans, start_trans, end_trans):
# emissions: (seq_length, batch_size, num_tags)
# mask: (seq_length, batch_size)
seq_length = emissions.shape[0]
# 将score设置为初始转移概率，并加上第一次发射概率
# shape: (batch_size, num_tags)
score = start_trans + emissions[0]
for i in range(1, seq_length):
# 扩展score的维度用于总score的计算
# shape: (batch_size, num_tags, 1)
broadcast_score = score.expand_dims(2)
# 扩展emission的维度用于总score的计算
# shape: (batch_size, 1, num_tags)
broadcast_emissions = emissions[i].expand_dims(1)
# 根据公式(7)，计算score_i
# 此时broadcast_score是由第0个到当前Token所有可能路径
# 对应score的log_sum_exp
# shape: (batch_size, num_tags, num_tags)
next_score = broadcast_score + trans + broadcast_emissions
# 对score_i做log_sum_exp运算，用于下一个Token的score计算
# shape: (batch_size, num_tags)
next_score = ops.logsumexp(next_score, axis=1)
# 当mask == 1时，score才会变化
# shape: (batch_size, num_tags)
score = mnp.where(mask[i].expand_dims(1), next_score, score)
# 最后加结束转移概率
# shape: (batch_size, num_tags)
score += end_trans
# 对所有可能的路径得分求log_sum_exp
# shape: (batch_size,)
return ops.logsumexp(score, axis=1)Viterbi算法
python
def viterbi_decode(emissions, mask, trans, start_trans, end_trans):
# emissions: (seq_length, batch_size, num_tags)
# mask: (seq_length, batch_size)
seq_length = mask.shape[0]
score = start_trans + emissions[0]
history = ()
for i in range(1, seq_length):
broadcast_score = score.expand_dims(2)
broadcast_emission = emissions[i].expand_dims(1)
next_score = broadcast_score + trans + broadcast_emission
# 求当前Token对应score取值最大的标签，并保存
indices = next_score.argmax(axis=1)
history += (indices,)
next_score = next_score.max(axis=1)
score = mnp.where(mask[i].expand_dims(1), next_score, score)
score += end_trans
return score, history
def post_decode(score, history, seq_length):
# 使用Score和History计算最佳预测序列
batch_size = seq_length.shape[0]
seq_ends = seq_length - 1
# shape: (batch_size,)
best_tags_list = []
# 依次对一个Batch中每个样例进行解码
for idx in range(batch_size):
# 查找使最后一个Token对应的预测概率最大的标签，
# 并将其添加至最佳预测序列存储的列表中
best_last_tag = score[idx].argmax(axis=0)
best_tags = [int(best_last_tag.asnumpy())]
# 重复查找每个Token对应的预测概率最大的标签，加入列表
for hist in reversed(history[:seq_ends[idx]]):
best_last_tag = hist[idx][best_tags[-1]]
best_tags.append(int(best_last_tag.asnumpy()))
# 将逆序求解的序列标签重置为正序
best_tags.reverse()
best_tags_list.append(best_tags)
return best_tags_listCRF层
完成上述前向训练和解码部分的代码后，将其组装完整的CRF层。考虑到输入序列可能存在Padding的情况，CRF的输入需要考虑输入序列的真实长度，因此除发射矩阵和标签外，加入seq_length参数传入序列Padding前的长度，并实现生成mask矩阵的sequence_mask方法。
综合上述代码，使用nn.Cell进行封装，最后实现完整的CRF层如下：
python
import mindspore as ms
import mindspore.nn as nn
import mindspore.ops as ops
import mindspore.numpy as mnp
from mindspore.common.initializer import initializer, Uniform
def sequence_mask(seq_length, max_length, batch_first=False):
"""根据序列实际长度和最大长度生成mask矩阵"""
range_vector = mnp.arange(0, max_length, 1, seq_length.dtype)
result = range_vector < seq_length.view(seq_length.shape + (1,))
if batch_first:
return result.astype(ms.int64)
return result.astype(ms.int64).swapaxes(0, 1)
class CRF(nn.Cell):
def __init__(self, num_tags: int, batch_first: bool = False, reduction: str = 'sum') -> None:
if num_tags <= 0:
raise ValueError(f'invalid number of tags: {num_tags}')
super().__init__()
if reduction not in ('none', 'sum', 'mean', 'token_mean'):
raise ValueError(f'invalid reduction: {reduction}')
self.num_tags = num_tags
self.batch_first = batch_first
self.reduction = reduction
self.start_transitions = ms.Parameter(initializer(Uniform(0.1), (num_tags,)), name='start_transitions')
self.end_transitions = ms.Parameter(initializer(Uniform(0.1), (num_tags,)), name='end_transitions')
self.transitions = ms.Parameter(initializer(Uniform(0.1), (num_tags, num_tags)), name='transitions')
def construct(self, emissions, tags=None, seq_length=None):
if tags is None:
return self._decode(emissions, seq_length)
return self._forward(emissions, tags, seq_length)
def _forward(self, emissions, tags=None, seq_length=None):
if self.batch_first:
batch_size, max_length = tags.shape
emissions = emissions.swapaxes(0, 1)
tags = tags.swapaxes(0, 1)
else:
max_length, batch_size = tags.shape
if seq_length is None:
seq_length = mnp.full((batch_size,), max_length, ms.int64)
mask = sequence_mask(seq_length, max_length)
# shape: (batch_size,)
numerator = compute_score(emissions, tags, seq_length-1, mask, self.transitions, self.start_transitions, self.end_transitions)
# shape: (batch_size,)
denominator = compute_normalizer(emissions, mask, self.transitions, self.start_transitions, self.end_transitions)
# shape: (batch_size,)
llh = denominator - numerator
if self.reduction == 'none':
return llh
if self.reduction == 'sum':
return llh.sum()
if self.reduction == 'mean':
return llh.mean()
return llh.sum() / mask.astype(emissions.dtype).sum()
def _decode(self, emissions, seq_length=None):
if self.batch_first:
batch_size, max_length = emissions.shape[:2]
emissions = emissions.swapaxes(0, 1)
else:
batch_size, max_length = emissions.shape[:2]
if seq_length is None:
seq_length = mnp.full((batch_size,), max_length, ms.int64)
mask = sequence_mask(seq_length, max_length)
return viterbi_decode(emissions, mask, self.transitions, self.start_transitions, self.end_transitions)BiLSTM+CRF模型
在实现CRF后，我们设计一个双向LSTM+CRF的模型来进行命名实体识别任务的训练。模型结构如下：nn.Embedding -> nn.LSTM -> nn.Dense -> CRF，其中LSTM提取序列特征，经过Dense层变换获得发射概率矩阵，最后送入CRF层。具体实现如下：
python
class BiLSTM_CRF(nn.Cell):
def __init__(self, vocab_size, embedding_dim, hidden_dim, num_tags, padding_idx=0):
super().__init__()
self.embedding = nn.Embedding(vocab_size, embedding_dim, padding_idx=padding_idx)
self.lstm = nn.LSTM(embedding_dim, hidden_dim // 2, bidirectional=True, batch_first=True)
self.hidden2tag = nn.Dense(hidden_dim, num_tags, 'he_uniform')
self.crf = CRF(num_tags, batch_first=True)
def construct(self, inputs, seq_length, tags=None):
embeds = self.embedding(inputs)
outputs, _ = self.lstm(embeds, seq_length=seq_length)
feats = self.hidden2tag(outputs)
crf_outs = self.crf(feats, tags, seq_length)
return crf_outs效果展示
此章节学习到此结束，感谢昇思平台。