Gensim Word2Vec从预训练模型中选择次要词向量集 [英] Gensim Word2Vec select minor set of word vectors from pretrained model

问题描述

我在gensim中有一个大型的预训练Word2Vec模型，从中我想将预训练的词向量用于我的Keras模型中的嵌入层.

I have a large pretrained Word2Vec model in gensim from which I want to use the pretrained word vectors for an embedding layer in my Keras model.

问题在于嵌入量很大，并且我不需要大多数单词向量(因为我知道哪些单词可以作为Input出现).因此，我想摆脱它们以减小嵌入层的大小.

The problem is that the embedding size is enormous and I don't need most of the word vectors (because I know which words can occure as Input). So I want to get rid of them to reduce the size of my embedding layer.

是否有一种方法可以根据单词白名单保留所需的单词矢量(包括对应的索引！)?

Is there a way to just keep desired wordvectors (including the coresponding indices!), based on a whitelist of words?

推荐答案

感谢此答案(我已经更改了代码，以使其变得更好).您可以使用此代码解决问题.

Thanks to this answer (I've changed the code a little bit to make it better). you can use this code for solving your problem.

我们在restricted_word_set中有所有次要的单词集(可以是列表或集合)，而w2v是我们的模型，所以这里是函数:

we have all our minor set of words in restricted_word_set(it can be either list or set) and w2v is our model, so here is the function:

import numpy as np

def restrict_w2v(w2v, restricted_word_set):
    new_vectors = []
    new_vocab = {}
    new_index2entity = []
    new_vectors_norm = []

    for i in range(len(w2v.vocab)):
        word = w2v.index2entity[i]
        vec = w2v.vectors[i]
        vocab = w2v.vocab[word]
        vec_norm = w2v.vectors_norm[i]
        if word in restricted_word_set:
            vocab.index = len(new_index2entity)
            new_index2entity.append(word)
            new_vocab[word] = vocab
            new_vectors.append(vec)
            new_vectors_norm.append(vec_norm)

    w2v.vocab = new_vocab
    w2v.vectors = np.array(new_vectors)
    w2v.index2entity = np.array(new_index2entity)
    w2v.index2word = np.array(new_index2entity)
    w2v.vectors_norm = np.array(new_vectors_norm)

警告:首次创建模型时，请按vectors_norm == None 如果在此使用此功能，将会得到一个错误. vectors_norm 首次使用后，将获得类型为numpy.ndarray的值.所以 在使用该功能之前，请尝试类似most_similar("cat")这样的操作 vectors_norm不等于None.

WARNING: when you first create the model the vectors_norm == None so you will get an error if you use this function there. vectors_norm will get a value of the type numpy.ndarray after the first use. so before using the function try something like most_similar("cat") so that vectors_norm not be equal to None.

它根据 Word2VecKeyedVectors .

用法:

w2v = KeyedVectors.load_word2vec_format("GoogleNews-vectors-negative300.bin.gz", binary=True)
w2v.most_similar("beer")

[('啤酒'，0.8409687876701355)，
("lager"，0.7733745574951172)，
(啤酒"，0.71753990650177)，
(饮料"，0.668931245803833)，
("lagers"，0.6570086479187012)，
('Yuengling_Lager'，0.655455470085144)，
('microbrew'，0.6534324884414673)，
('Brooklyn_Lager'，0.6501551866531372)，
('suds'，0.6497018337249756)，
("brewed_beer"，0.6490240097045898)

[('beers', 0.8409687876701355),
('lager', 0.7733745574951172),
('Beer', 0.71753990650177),
('drinks', 0.668931245803833),
('lagers', 0.6570086479187012),
('Yuengling_Lager', 0.655455470085144),
('microbrew', 0.6534324884414673),
('Brooklyn_Lager', 0.6501551866531372),
('suds', 0.6497018337249756),
('brewed_beer', 0.6490240097045898)]

restricted_word_set = {"beer", "wine", "computer", "python", "bash", "lagers"}
restrict_w2v(w2v, restricted_word_set)
w2v.most_similar("beer")

[('lagers'，0.6570085287094116)，
(葡萄酒"，0.6217695474624634)，
("bash"，0.20583480596542358)，
(计算机"，0.06677375733852386)，
("python"，0.005948573350906372)]

[('lagers', 0.6570085287094116),
('wine', 0.6217695474624634),
('bash', 0.20583480596542358),
('computer', 0.06677375733852386),
('python', 0.005948573350906372)]

它也可以用于删除一些单词.

it can be used for removing some words either.

这篇关于Gensim Word2Vec从预训练模型中选择次要词向量集的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！