nlp fasttext

fasttext用于词向量和文本分类，使用词袋以及n-gram袋表征语句

n-gram实现

    def biGramHash(sequence, t, buckets):
        t1 = sequence[t - 1] if t - 1 >= 0 else 0
        return (t1 * 14918087) % buckets

    def triGramHash(sequence, t, buckets):
        t1 = sequence[t - 1] if t - 1 >= 0 else 0
        t2 = sequence[t - 2] if t - 2 >= 0 else 0
        return (t2 * 14918087 * 18408749 + t1 * 14918087) % buckets

n-gram和CBOW很相似都是通过周边的词预测，只不过n-gram只一边。

model

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.embedding_ngram2 = nn.Embedding(config.n_gram_vocab, config.embed)
        self.embedding_ngram3 = nn.Embedding(config.n_gram_vocab, config.embed)
        self.dropout = nn.Dropout(config.dropout)
        self.fc1 = nn.Linear(config.embed * 3, config.hidden_size)
        # self.dropout2 = nn.Dropout(config.dropout)
        self.fc2 = nn.Linear(config.hidden_size, config.num_classes)

    def forward(self, x):
        out_word = self.embedding(x[0])
        out_bigram = self.embedding_ngram2(x[2])
        out_trigram = self.embedding_ngram3(x[3])
        out = torch.cat((out_word, out_bigram, out_trigram), -1)
        out = out.mean(dim=1)
        out = self.dropout(out)
        out = self.fc1(out)
        out = F.relu(out)
        out = self.fc2(out)
        return out