動手學深度學習PyTorch版-詞嵌入進階

詞嵌入進階

載入與訓練Glove向量

import torch
import torchtext.vocab as vocab

print([key for key in vocab.pretrained_aliases.keys() if "glove" in key])
cache_dir = "/home/kesci/input/GloVe6B5429"
glove = vocab.GloVe(name='6B', dim=50, cache=cache_dir)
print("一共包含%d個詞。" % len(glove.stoi))
print(glove.stoi['beautiful'], glove.itos[3366])

求近義詞和類比詞

def knn(W, x, k):
    '''
    @params:
        W: 所有向量的集合
        x: 給定向量
        k: 查詢的數量
    @outputs:
        topk: 餘弦相似性最大k個的下標
        [...]: 餘弦相似度
    '''
    cos = torch.matmul(W, x.view((-1,))) / (
        (torch.sum(W * W, dim=1) + 1e-9).sqrt() * torch.sum(x * x).sqrt())
    _, topk = torch.topk(cos, k=k)
    topk = topk.cpu().numpy()
    return topk, [cos[i].item() for i in topk]

def get_similar_tokens(query_token, k, embed):
    '''
    @params:
        query_token: 給定的單詞
        k: 所需近義詞的個數
        embed: 預訓練詞向量
    '''
    topk, cos = knn(embed.vectors,
                    embed.vectors[embed.stoi[query_token]], k+1)
    for i, c in zip(topk[1:], cos[1:]):  # 除去輸入詞
        print('cosine sim=%.3f: %s' % (c, (embed.itos[i])))

get_similar_tokens('chip', 3, glove)

求類比詞

def get_analogy(token_a, token_b, token_c, embed):
    '''
    @params:
        token_a: 詞a
        token_b: 詞b
        token_c: 詞c
        embed: 預訓練詞向量
    @outputs:
        res: 類比詞d
    '''
    vecs = [embed.vectors[embed.stoi[t]] 
                for t in [token_a, token_b, token_c]]
    x = vecs[1] - vecs[0] + vecs[2]
    topk, cos = knn(embed.vectors, x, 1)
    res = embed.itos[topk[0]]
    return res

get_analogy('man', 'woman', 'son', glove)```