我在哪里可以找到word2vec经过一些英文文章训练的可靠模型？
我需要一个word2vec黑盒子，例如，我可以将一个句子作为数组传递：
["London", "is", "the", "capital", "of", "Great", "Britain"]
并收到：
[some_vector_of_floats1, some_vector_of_floats2, some_vector_of_floats3, some_vector_of_floats4, some_vector_of_floats5, some_vector_of_floats6, some_vector_of_floats7]
在 Python 中，您可以使用Gensim
import gensim
model = gensim.models.Word2Vec.load_word2vec_format('path-to-vectors.txt', binary=False)
# if you vector file is in binary format, change to binary=True
sentence = ["London", "is", "the", "capital", "of", "Great", "Britain"]
vectors = [model[w] for w in sentence]
这些向量应该比使用 word2vec 获得的预训练向量提供更好的性能。
我稍微修改了代码 - 出于我的目的
vocab = model.vocab.keys()
sentence = ["London", "is", "the", "capital", "of", "Great", "Britain"]
vectors=[]
for w in sentence:
if w in vocab:
vectors.append(model[w])
else:
print("Word {} not in vocab".format(w))
vectors.append([0])
你也可以使用 try/catch - 你的电话。