word2vec两种训练方法

Word2Vec类介绍

定义

def __init__(self, sentences=None, size=100, alpha=0.025, window=5, min_count=5,
                 max_vocab_size=None, sample=1e-3, seed=1, workers=3, min_alpha=0.0001,
                 sg=0, hs=0, negative=5, cbow_mean=1, hashfxn=hash, iter=5, null_word=0,
                 trim_rule=None, sorted_vocab=1, batch_words=MAX_WORDS_IN_BATCH, compute_loss=False, callbacks=()):

常用参数

sentences：数据类型为list，可以用BrownCorpus,Text8Corpus或lineSentence来构建sentences
size：向量维度，默认为100
window：当前词与预测次在一个句子中最大距离是多少
min_count：用于字典阶段，词频少于min_count次数的单词会被丢弃掉，默认为5
workers：控制训练的并行数
sg：训练算法，默认为0，对应CBOW算法，sg为1采用skip-gram算法

训练方式一：

dim=300
embedding_size = dim
model = gensim.models.Word2Vec(LineSentence(model_dir + 'train_word.txt'),
                               size=embedding_size,
                               window=5,
                               min_count=10,
                               workers=multiprocessing.cpu_count())

model.save(model_dir + "word2vec_gensim"+str(embedding_size)+".w2v")
model.wv.save_word2vec_format(model_dir + "word2vec_gensim_300d.txt", binary=False)

训练方式2：

documents = list(LineSentence(model_dir + 'train_word.txt'))
print(len(documents))
print(documents[:10])
model = gensim.models.Word2Vec(documents, size=300)
model.train(documents, total_examples=len(documents), epochs=10)
model.save("./input/word2vec.w2v")
model.wv.save_word2vec_format("./input/word_gensim_300d.txt", binary=False)