使用 TensorFlow 进行多标签文本分类

Question

文本数据被组织为具有 20,000 个元素的向量，例如 [2, 1, 0, 0, 5, ...., 0]。第 i 个元素表示第 i 个词在文本中出现的频率。

地面实况标签数据也表示为具有 4,000 个元素的向量，例如 [0, 0, 1, 0, 1, ...., 0]。第 i 个元素表示第 i 个标签是否是文本的正标签。文本的标签数量因文本而异。

我有一个单标签文本分类代码。

如何为多标签文本分类编辑以下代码？

特别想知道以下几点。

如何使用 TensorFlow 计算准确率。
如何设置判断标签是正负的阈值。例如，如果输出为 [0.80, 0.43, 0.21, 0.01, 0.32]，ground truth 为 [1, 1, 0, 0, 1]，则得分超过 0.25 的标签应被判断为正。

谢谢。

import tensorflow as tf

# hidden Layer
class HiddenLayer(object):
    def __init__(self, input, n_in, n_out):
        self.input = input

        w_h = tf.Variable(tf.random_normal([n_in, n_out],mean = 0.0,stddev = 0.05))
        b_h = tf.Variable(tf.zeros([n_out]))

        self.w = w_h
        self.b = b_h
        self.params = [self.w, self.b]

    def output(self):
        linarg = tf.matmul(self.input, self.w) + self.b
        self.output = tf.nn.relu(linarg)

        return self.output

# output Layer
class OutputLayer(object):
    def __init__(self, input, n_in, n_out):
        self.input = input

        w_o = tf.Variable(tf.random_normal([n_in, n_out], mean = 0.0, stddev = 0.05))
        b_o = tf.Variable(tf.zeros([n_out]))

        self.w = w_o
        self.b = b_o
        self.params = [self.w, self.b]

    def output(self):
        linarg = tf.matmul(self.input, self.w) + self.b
        self.output = tf.nn.relu(linarg)

        return self.output

# model
def model():
    h_layer = HiddenLayer(input = x, n_in = 20000, n_out = 1000)
    o_layer = OutputLayer(input = h_layer.output(), n_in = 1000, n_out = 4000)

    # loss function
    out = o_layer.output()
    cross_entropy = -tf.reduce_sum(y_*tf.log(out + 1e-9), name='xentropy')    

    # regularization
    l2 = (tf.nn.l2_loss(h_layer.w) + tf.nn.l2_loss(o_layer.w))
    lambda_2 = 0.01

    # compute loss
    loss = cross_entropy + lambda_2 * l2

    # compute accuracy for single label classification task
    correct_pred = tf.equal(tf.argmax(out, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, "float"))

    return loss, accuracy

Answer 1

您必须使用其他交叉熵函数的变体来支持多标签分类。如果你的输出少于一千，你应该使用 sigmoid_cross_entropy_with_logits, in your case that you have 4000 outputs you may consider candidate sampling，因为它比以前的更快。

How to compute accuracy using TensorFlow.

这取决于您的问题和您想要实现的目标。如果您不想遗漏图像中的任何对象，那么如果分类器除了一个对象之外一切正常，那么您应该将整个图像视为一个错误。您还可以认为错过或错误分类的对象是一个错误。后者我认为 sigmoid_cross_entropy_with_logits.

支持

How to set a threshold which judges whether a label is positive or negative. For instance, if the output is [0.80, 0.43, 0.21, 0.01, 0.32] and the ground truth is [1, 1, 0, 0, 1], the labels with scores over 0.25 should be judged as positive.

门槛是一种方式，你必须决定选择哪一种。但那是某种 hack，不是真正的多标签分类。为此，您需要我之前说过的功能。

Answer 2

将relu改为输出层的sigmoid。将交叉熵损失修改为 sigmoid 交叉熵损失的显式数学公式（显式损失在我的 case/version of tensorflow 中起作用）

import tensorflow as tf

# hidden Layer
class HiddenLayer(object):
    def __init__(self, input, n_in, n_out):
        self.input = input

        w_h = tf.Variable(tf.random_normal([n_in, n_out],mean = 0.0,stddev = 0.05))
        b_h = tf.Variable(tf.zeros([n_out]))

        self.w = w_h
        self.b = b_h
        self.params = [self.w, self.b]

    def output(self):
        linarg = tf.matmul(self.input, self.w) + self.b
        self.output = tf.nn.relu(linarg)

        return self.output

# output Layer
class OutputLayer(object):
    def __init__(self, input, n_in, n_out):
        self.input = input

        w_o = tf.Variable(tf.random_normal([n_in, n_out], mean = 0.0, stddev = 0.05))
        b_o = tf.Variable(tf.zeros([n_out]))

        self.w = w_o
        self.b = b_o
        self.params = [self.w, self.b]

    def output(self):
        linarg = tf.matmul(self.input, self.w) + self.b
        #changed relu to sigmoid
        self.output = tf.nn.sigmoid(linarg)

        return self.output

# model
def model():
    h_layer = HiddenLayer(input = x, n_in = 20000, n_out = 1000)
    o_layer = OutputLayer(input = h_layer.output(), n_in = 1000, n_out = 4000)

    # loss function
    out = o_layer.output()
    # modified cross entropy to explicit mathematical formula of sigmoid cross entropy loss
    cross_entropy = -tf.reduce_sum( (  (y_*tf.log(out + 1e-9)) + ((1-y_) * tf.log(1 - out + 1e-9)) )  , name='xentropy' )    

    # regularization
    l2 = (tf.nn.l2_loss(h_layer.w) + tf.nn.l2_loss(o_layer.w))
    lambda_2 = 0.01

    # compute loss
    loss = cross_entropy + lambda_2 * l2

    # compute accuracy for single label classification task
    correct_pred = tf.equal(tf.argmax(out, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, "float"))

    return loss, accuracy

使用 TensorFlow 进行多标签文本分类

Multilabel Text Classification using TensorFlow

python

tensorflow

text-classification

multilabel-classification