NLP系列——文本分类

目录

1. TextCNN

2. TextRNN

3. TextRNN + Attention

4. TextRCNN

---

Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.convs = nn.ModuleList(
            [nn.Conv2d(1, config.num_filters, (k, config.embed)) for k in config.filter_sizes])
        self.dropout = nn.Dropout(config.dropout)
        self.fc = nn.Linear(config.num_filters * len(config.filter_sizes), config.num_classes)

    def conv_and_pool(self, x, conv):
        x = F.relu(conv(x)).squeeze(3)  # [128, 256, 31]
        x = F.max_pool1d(x, x.size(2)).squeeze(2)  # [128, 256]
        return x

    def forward(self, x):
        out = self.embedding(x[0])  # [128, 32, 300], 32表示句子最大长度, x[0]是句子, x[1]是标签
        out = out.unsqueeze(1)  # [128, 1, 32, 300]
        out = torch.cat([self.conv_and_pool(out, conv) for conv in self.convs], 1)  # [128, 768], 768=3*256, 3表示卷积核数量
        out = self.dropout(out)
        out = self.fc(out)  # [128, 10]
        return out

---

class Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,
                            bidirectional=True, batch_first=True, dropout=config.dropout)
        self.fc = nn.Linear(config.hidden_size * 2, config.num_classes)

    def forward(self, x):
        x, _ = x
        out = self.embedding(x)  # [batch_size, seq_len, embedding]=[128, 32, 300]
        out, _ = self.lstm(out)
        out = self.fc(out[:, -1, :])  # 句子最后时刻的输出
        return out

---

class Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,
                            bidirectional=True, batch_first=True, dropout=config.dropout)
        self.tanh1 = nn.Tanh()
        self.w = nn.Parameter(torch.Tensor(config.hidden_size * 2))
        self.tanh2 = nn.Tanh()
        self.fc1 = nn.Linear(config.hidden_size * 2, config.hidden_size2)
        self.fc = nn.Linear(config.hidden_size2, config.num_classes)

    def forward(self, x):
        x, _ = x
        emb = self.embedding(x)  # [batch_size, seq_len, embedding]=[128, 32, 300]
        H, _ = self.lstm(emb)  # [batch_size, seq_len, hidden_size * num_direction]=[128, 32, 256]
        M = self.tanh1(H)  # [128, 32, 256]
        alpha = F.softmax(torch.matmul(M, self.w), dim=1).unsqueeze(-1)  # [128, 32, 1]
        out = H * alpha  # [128, 32, 256]
        out = torch.sum(out, 1)  # [128, 256]
        out = F.relu(out)
        out = self.fc1(out)
        out = self.fc(out)  # [128, 64]
        return out

---

class Model(nn.Module):
    def __init__(self, config):
        super(Model, self).__init__()
        if config.embedding_pretrained is not None:
            self.embedding = nn.Embedding.from_pretrained(config.embedding_pretrained, freeze=False)
        else:
            self.embedding = nn.Embedding(config.n_vocab, config.embed, padding_idx=config.n_vocab - 1)
        self.lstm = nn.LSTM(config.embed, config.hidden_size, config.num_layers,
                            bidirectional=True, batch_first=True, dropout=config.dropout)
        self.maxpool = nn.MaxPool1d(config.pad_size)
        self.fc = nn.Linear(config.hidden_size * 2 + config.embed, config.num_classes)

    def forward(self, x):
        x, _ = x
        embed = self.embedding(x)  # [batch_size, seq_len, embedding]
        out, _ = self.lstm(embed)
        out = torch.cat((embed, out), 2)
        out = F.relu(out)
        out = out.permute(0, 2, 1)
        out = self.maxpool(out).squeeze()  # [batch_size, hidden_size*2 + embedding]
        out = self.fc(out)
        return out

上面代码中用的是双向RNN，论文中貌似是两个单向RNN