文本分类-PyTorch

文本分类步骤

一、文本预处理

1. 读取文本

with open(os.path.join(folder_name, file), 'rb') as f:
                review = f.read().decode('utf-8').replace('\n', '').lower()
                data.append([review, 1 if label == 'pos' else 0])

2. 对文本进行tokenize：根据文本的格式进行单词的切分
3. 创建vocab词典：利用 torchtext.vocab.Vocab 创建词典。
4. stoi：将数据集的文本从字符串的形式转换为单词下标序列的形式
5. clip or pad：通过截断或填充，得到定长文本
6. 对train data和test data创建数据迭代器：Data.TensorDataset，Data.DataLoader。

二、文本分类器

LSTM

class BiRNN(nn.Module):
    def __init__(self, vocab, embed_size, num_hiddens, num_layers):
        '''
        @params:
            vocab: 在数据集上创建的词典，用于获取词典大小
            embed_size: 嵌入维度大小
            num_hiddens: 隐藏状态维度大小
            num_layers: 隐藏层个数
        '''
        super(BiRNN, self).__init__()
        self.embedding = nn.Embedding(len(vocab), embed_size)
        
        # encoder-decoder framework
        # bidirectional设为True即得到双向循环神经网络
        self.encoder = nn.LSTM(input_size=embed_size, 
                                hidden_size=num_hiddens, 
                                num_layers=num_layers,
                                bidirectional=True)
        self.decoder = nn.Linear(4*num_hiddens, 2) # 初始时间步和最终时间步的隐藏状态作为全连接层输入
        
    def forward(self, inputs):
        '''
        @params:
            inputs: 词语下标序列，形状为 (batch_size, seq_len) 的整数张量
        @return:
            outs: 对文本情感的预测，形状为 (batch_size, 2) 的张量
        '''
        # 因为LSTM需要将序列长度(seq_len)作为第一维，所以需要将输入转置
        embeddings = self.embedding(inputs.permute(1, 0)) # (seq_len, batch_size, d)
        # rnn.LSTM 返回输出、隐藏状态和记忆单元，格式如 outputs, (h, c)
        outputs, _ = self.encoder(embeddings) # (seq_len, batch_size, 2*h)
        encoding = torch.cat((outputs[0], outputs[-1]), -1) # (batch_size, 4*h)
        outs = self.decoder(encoding) # (batch_size, 2)
        return outs

embed_size, num_hiddens, num_layers = 100, 100, 2
net = BiRNN(vocab, embed_size, num_hiddens, num_layers)

CNN

class TextCNN(nn.Module):
    def __init__(self, vocab, embed_size, kernel_sizes, num_channels):
        '''
        @params:
            vocab: 在数据集上创建的词典，用于获取词典大小
            embed_size: 嵌入维度大小
            kernel_sizes: 卷积核大小列表
            num_channels: 卷积通道数列表
        '''
        super(TextCNN, self).__init__()
        self.embedding = nn.Embedding(len(vocab), embed_size) # 参与训练的嵌入层
        self.constant_embedding = nn.Embedding(len(vocab), embed_size) # 不参与训练的嵌入层
        
        self.pool = GlobalMaxPool1d() # 时序最大池化层没有权重，所以可以共用一个实例
        self.convs = nn.ModuleList()  # 创建多个一维卷积层
        for c, k in zip(num_channels, kernel_sizes):
            self.convs.append(nn.Conv1d(in_channels = 2*embed_size, 
                                        out_channels = c, 
                                        kernel_size = k))
            
        self.decoder = nn.Linear(sum(num_channels), 2)
        self.dropout = nn.Dropout(0.5) # 丢弃层用于防止过拟合

    def forward(self, inputs):
        '''
        @params:
            inputs: 词语下标序列，形状为 (batch_size, seq_len) 的整数张量
        @return:
            outputs: 对文本情感的预测，形状为 (batch_size, 2) 的张量
        '''
        embeddings = torch.cat((
            self.embedding(inputs), 
            self.constant_embedding(inputs)), dim=2) # (batch_size, seq_len, 2*embed_size)
        # 根据一维卷积层要求的输入格式，需要将张量进行转置
        embeddings = embeddings.permute(0, 2, 1) # (batch_size, 2*embed_size, seq_len)
        
        encoding = torch.cat([
            self.pool(F.relu(conv(embeddings))).squeeze(-1) for conv in self.convs], dim=1)
        # encoding = []
        # for conv in self.convs:
        #     out = conv(embeddings) # (batch_size, out_channels, seq_len-kernel_size+1)
        #     out = self.pool(F.relu(out)) # (batch_size, out_channels, 1)
        #     encoding.append(out.squeeze(-1)) # (batch_size, out_channels)
        # encoding = torch.cat(encoding) # (batch_size, out_channels_sum)
        
        # 应用丢弃法后使用全连接层得到输出
        outputs = self.decoder(self.dropout(encoding))
        return outputs

embed_size, kernel_sizes, nums_channels = 100, [3, 4, 5], [100, 100, 100]
net = TextCNN(vocab, embed_size, kernel_sizes, nums_channels)

预训练词向量加载

cache_dir = "/home/kesci/input/GloVe6B5429"
glove_vocab = Vocab.GloVe(name='6B', dim=100, cache=cache_dir)

def load_pretrained_embedding(words, pretrained_vocab):
    '''
    @params:
        words: 需要加载词向量的词语列表，以 itos (index to string) 的词典形式给出
        pretrained_vocab: 预训练词向量
    @return:
        embed: 加载到的词向量
    '''
    embed = torch.zeros(len(words), pretrained_vocab.vectors[0].shape[0]) # 初始化为0
    oov_count = 0 # out of vocabulary
    for i, word in enumerate(words):
        try:
            idx = pretrained_vocab.stoi[word]
            embed[i, :] = pretrained_vocab.vectors[idx]
        except KeyError:
            oov_count += 1
    if oov_count > 0:
        print("There are %d oov words." % oov_count)
    return embed

net.embedding.weight.data.copy_(load_pretrained_embedding(vocab.itos, glove_vocab))
net.embedding.weight.requires_grad = False # 直接加载预训练好的, 所以不需要更新它