序列标注算法评估模块 seqeval 的使用
共 7468字,需浏览 15分钟
·
2020-11-25 22:30
在NLP中,序列标注算法是常见的深度学习模型,但是,对于序列标注算法的评估,我们真的熟悉吗?
在本文中,笔者将会序列标注算法的模型效果评估方法和seqeval
的使用。
序列标注算法的模型效果评估
在序列标注算法中,一般我们会形成如下的序列列表,如下:
['O', 'O', 'B-MISC', 'I-MISC', 'B-MISC', 'I-MISC', 'O', 'B-PER', 'I-PER']
一般序列标注算法的格式有BIO
,IOBES
,BMES
等。其中,实体
指的是从B开头标签开始的,同一类型(比如:PER/LOC/ORG)的,非O的连续标签序列。
常见的序列标注算法的模型效果评估指标有准确率(accuracy)、查准率(percision)、召回率(recall)、F1值等,计算的公式如下:
准确率: accuracy = 预测对的元素个数/总的元素个数
查准率:precision = 预测正确的实体个数 / 预测的实体总个数
召回率:recall = 预测正确的实体个数 / 标注的实体总个数
F1值:F1 = 2 *准确率 * 召回率 / (准确率 + 召回率)
举个例子,我们有如下的真实序列y_true
和预测序列y_pred
,如下:
y_true = ['O', 'O', 'O', 'B-MISC', 'I-MISC', 'I-MISC', 'O', 'B-PER', 'I-PER']
y_pred = ['O', 'O', 'B-MISC', 'I-MISC', 'B-MISC', 'I-MISC', 'O', 'B-PER', 'I-PER']
列表中一个有9个元素,其中预测对的元素个数为6个,那么准确率为2/3。标注的实体总个数为2个,预测的实体总个数为3个,预测正确的实体个数为1个,那么precision=1/3, recall=1/2, F1=0.4。
seqeval的使用
一般我们的序列标注算法,是用conlleval.pl
脚本实现,但这是用perl语言实现的。在Python中,也有相应的序列标注算法的模型效果评估的第三方模块,那就是seqeval
,其官网网址为:https://pypi.org/project/seqeval/0.0.3/ 。
seqeval
支持BIO
,IOBES
标注模式,可用于命名实体识别,词性标注,语义角色标注等任务的评估。
官网文档中给出了两个例子,笔者修改如下:
例子1:
# -*- coding: utf-8 -*-
from seqeval.metrics import f1_score
from seqeval.metrics import precision_score
from seqeval.metrics import accuracy_score
from seqeval.metrics import recall_score
from seqeval.metrics import classification_report
y_true = ['O', 'O', 'O', 'B-MISC', 'I-MISC', 'I-MISC', 'O', 'B-PER', 'I-PER']
y_pred = ['O', 'O', 'B-MISC', 'I-MISC', 'B-MISC', 'I-MISC', 'O', 'B-PER', 'I-PER']
print("accuary: ", accuracy_score(y_true, y_pred))
print("p: ", precision_score(y_true, y_pred))
print("r: ", recall_score(y_true, y_pred))
print("f1: ", f1_score(y_true, y_pred))
print("classification report: ")
print(classification_report(y_true, y_pred))
输出结果如下:
accuary: 0.6666666666666666
p: 0.3333333333333333
r: 0.5
f1: 0.4
classification report:
precision recall f1-score support
MISC 0.00 0.00 0.00 1
PER 1.00 1.00 1.00 1
micro avg 0.33 0.50 0.40 2
macro avg 0.50 0.50 0.50 2
例子2:
# -*- coding: utf-8 -*-
from seqeval.metrics import f1_score
from seqeval.metrics import precision_score
from seqeval.metrics import accuracy_score
from seqeval.metrics import recall_score
from seqeval.metrics import classification_report
y_true = [['O', 'O', 'O', 'B-MISC', 'I-MISC', 'I-MISC', 'O'], ['B-PER', 'I-PER']]
y_pred = [['O', 'O', 'B-MISC', 'I-MISC', 'B-MISC', 'I-MISC', 'O'], ['B-PER', 'I-PER']]
print("accuary: ", accuracy_score(y_true, y_pred))
print("p: ", precision_score(y_true, y_pred))
print("r: ", recall_score(y_true, y_pred))
print("f1: ", f1_score(y_true, y_pred))
print("classification report: ")
print(classification_report(y_true, y_pred))
输出结果同上。
在Keras中使用seqeval
笔者一年多年写过文章:使用CRF++实现命名实体识别(NER), 我们对模型训练部分的代码加以改造,使之在训练过程中能输出F1值。
在Github上下载项目DL_4_NER
,网址为:https://github.com/percent4/DL_4_NER 。修改utils.py中的文件夹路径,以及模型训练部分的代码(DL_4_NER/Bi_LSTM_Model_training.py)如下:
# -*- coding: utf-8 -*-
import pickle
import numpy as np
import pandas as pd
from utils import BASE_DIR, CONSTANTS, load_data
from data_processing import data_processing
from keras.utils import np_utils, plot_model
from keras.models import Sequential
from keras.preprocessing.sequence import pad_sequences
from keras.layers import Bidirectional, LSTM, Dense, Embedding, TimeDistributed
# 模型输入数据
def input_data_for_model(input_shape):
# 数据导入
input_data = load_data()
# 数据处理
data_processing()
# 导入字典
with open(CONSTANTS[1], 'rb') as f:
word_dictionary = pickle.load(f)
with open(CONSTANTS[2], 'rb') as f:
inverse_word_dictionary = pickle.load(f)
with open(CONSTANTS[3], 'rb') as f:
label_dictionary = pickle.load(f)
with open(CONSTANTS[4], 'rb') as f:
output_dictionary = pickle.load(f)
vocab_size = len(word_dictionary.keys())
label_size = len(label_dictionary.keys())
# 处理输入数据
aggregate_function = lambda input: [(word, pos, label) for word, pos, label in
zip(input['word'].values.tolist(),
input['pos'].values.tolist(),
input['tag'].values.tolist())]
grouped_input_data = input_data.groupby('sent_no').apply(aggregate_function)
sentences = [sentence for sentence in grouped_input_data]
x = [[word_dictionary[word[0]] for word in sent] for sent in sentences]
x = pad_sequences(maxlen=input_shape, sequences=x, padding='post', value=0)
y = [[label_dictionary[word[2]] for word in sent] for sent in sentences]
y = pad_sequences(maxlen=input_shape, sequences=y, padding='post', value=0)
y = [np_utils.to_categorical(label, num_classes=label_size + 1) for label in y]
return x, y, output_dictionary, vocab_size, label_size, inverse_word_dictionary
# 定义深度学习模型:Bi-LSTM
def create_Bi_LSTM(vocab_size, label_size, input_shape, output_dim, n_units, out_act, activation):
model = Sequential()
model.add(Embedding(input_dim=vocab_size + 1, output_dim=output_dim,
input_length=input_shape, mask_zero=True))
model.add(Bidirectional(LSTM(units=n_units, activation=activation,
return_sequences=True)))
model.add(TimeDistributed(Dense(label_size + 1, activation=out_act)))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
return model
# 模型训练
def model_train():
# 将数据集分为训练集和测试集,占比为9:1
input_shape = 60
x, y, output_dictionary, vocab_size, label_size, inverse_word_dictionary = input_data_for_model(input_shape)
train_end = int(len(x)*0.9)
train_x, train_y = x[0:train_end], np.array(y[0:train_end])
test_x, test_y = x[train_end:], np.array(y[train_end:])
# 模型输入参数
activation = 'selu'
out_act = 'softmax'
n_units = 100
batch_size = 32
epochs = 10
output_dim = 20
# 模型训练
lstm_model = create_Bi_LSTM(vocab_size, label_size, input_shape, output_dim, n_units, out_act, activation)
lstm_model.fit(train_x, train_y, validation_data=(test_x, test_y), epochs=epochs, batch_size=batch_size, verbose=1)
model_train()
模型训练的结果如下(中间过程省略):
......
12598/12598 [==============================] - 26s 2ms/step - loss: 0.0075 - acc: 0.9981 - val_loss: 0.2131 - val_acc: 0.9592
我们修改代码,在lstm_model.fit那一行修改代码如下:
lables = ['O', 'B-MISC', 'I-MISC', 'B-ORG', 'I-ORG', 'B-PER', 'B-LOC', 'I-PER', 'I-LOC', 'sO']
id2label = dict(zip(range(len(lables)), lables))
callbacks = [F1Metrics(id2label)]
lstm_model.fit(train_x, train_y, validation_data=(test_x, test_y), epochs=epochs,
batch_size=batch_size, verbose=1, callbacks=callbacks)
此时输出结果为:
12598/12598 [==============================] - 26s 2ms/step - loss: 0.0089 - acc: 0.9978 - val_loss: 0.2145 - val_acc: 0.9560
- f1: 95.40
precision recall f1-score support
MISC 0.9707 0.9833 0.9769 15844
PER 0.9080 0.8194 0.8614 1157
LOC 0.7517 0.8095 0.7795 677
ORG 0.8290 0.7289 0.7757 745
sO 0.7757 0.8300 0.8019 100
micro avg 0.9524 0.9556 0.9540 18523
macro avg 0.9520 0.9556 0.9535 18523
这就是seqeval的强大之处。
关于seqeval在Keras的使用,有不清楚的地方可以参考该项目的Github网址:https://github.com/chakki-works/seqeval 。
推荐阅读
点击下方阅读原文加入社区会员
点赞鼓励一下