文本分类是自然语言处理的一个常见任务,它把一段不定长的文本序列变换为文本的类别。本节关注它的一个子问题:使用文本情感分类来分析文本作者的情绪。这个问题也叫情感分析,并有着广泛的应用。
同搜索近义词和类比词一样,文本分类也属于词嵌入的下游应用。在本节中,我们将应用预训练的词向量和含多个隐藏层的双向循环神经网络与卷积神经网络,来判断一段不定长的文本序列中包含的是正面还是负面的情绪。后续内容将从以下几个方面展开:
文本情感分类数据集
使用循环神经网络进行情感分类
使用卷积神经网络进行情感分类
训练模型
训练时可以调用之前编写的 train 及 evaluate_accuracy 函数。
def evaluate_accuracy(data_iter, net, device=None):
if device is None and isinstance(net, torch.nn.Module):
device = list(net.parameters())[0].device
acc_sum, n = 0.0, 0
with torch.no_grad():
for X, y in data_iter:
if isinstance(net, torch.nn.Module):
net.eval()
acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
net.train()
else:
if('is_training' in net.__code__.co_varnames):
acc_sum += (net(X, is_training=False).argmax(dim=1) == y).float().sum().item()
else:
acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
n += y.shape[0]
return acc_sum / n
def train(train_iter, test_iter, net, loss, optimizer, device, num_epochs):
net = net.to(device)
print("training on ", device)
batch_count = 0
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n, start = 0.0, 0.0, 0, time.time()
for X, y in train_iter:
X = X.to(device)
y = y.to(device)
y_hat = net(X)
l = loss(y_hat, y)
optimizer.zero_grad()
l.backward()
optimizer.step()
train_l_sum += l.cpu().item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().cpu().item()
n += y.shape[0]
batch_count += 1
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f, time %.1f sec'
% (epoch + 1, train_l_sum / batch_count, train_acc_sum / n, test_acc, time.time() - start))