零基础入门NLP - 新闻文本分类 | 天池 | Task5 基于深度学习的文本分类2

Word2vec

from gensim.models.word2vec import Word2Vec
model = Word2Vec(sentences, workers=num_workers, size=num_features)

 

TextCNN

模型构建

self.filter_sizes = [2, 3, 4]  # n-gram window
self.out_channel = 100
self.convs = nn.ModuleList([nn.Conv2d(1, self.out_channel, (filter_size, input_size), bias=True) for filter_size in self.filter_sizes])

前向传播

pooled_outputs = []
for i in range(len(self.filter_sizes)):
    filter_height = sent_len - self.filter_sizes[i] + 1
    conv = self.convs[i](batch_embed)
    hidden = F.relu(conv)  # sen_num x out_channel x filter_height x 1

    mp = nn.MaxPool2d((filter_height, 1))  # (filter_height, filter_width)
    # sen_num x out_channel x 1 x 1 -> sen_num x out_channel
    pooled = mp(hidden).reshape(sen_num, self.out_channel)
    
    pooled_outputs.append(pooled)

 

TextRNN

模型搭建

input_size = config.word_dims

self.word_lstm = LSTM(
    input_size=input_size,
    hidden_size=config.word_hidden_size,
    num_layers=config.word_num_layers,
    batch_first=True,
    bidirectional=True,
    dropout_in=config.dropout_input,
    dropout_out=config.dropout_hidden,
)

前向传播

hiddens, _ = self.word_lstm(batch_embed, batch_masks)  # sent_len x sen_num x hidden*2
hiddens.transpose_(1, 0)  # sen_num x sent_len x hidden*2

if self.training:
    hiddens = drop_sequence_sharedmask(hiddens, self.dropout_mlp)