Question

我试图通过将来自google word2vec网站（freebase-vectors-skipgram1000.bin.gz）的预训练.bin文件加载到word2vec的gensim实现中来开始。模型加载正常，

使用..

model = word2vec.Word2Vec.load_word2vec_format('...../free....-en.bin', binary= True)

并创建一个

>>> print model
<gensim.models.word2vec.Word2Vec object at 0x105d87f50>

但是当我运行最相似的功能时。它无法找到词汇中的单词。我的错误代码如下。

我出错的任何想法？

>>> model.most_similar(['girl', 'father'], ['boy'], topn=3)
2013-10-11 10:22:00,562 : WARNING : word ‘girl’ not in vocabulary; ignoring it
2013-10-11 10:22:00,562 : WARNING : word ‘father’ not in vocabulary; ignoring it
2013-10-11 10:22:00,563 : WARNING : word ‘boy’ not in vocabulary; ignoring it
Traceback (most recent call last):
File “”, line 1, in
File “/....../anaconda/python.app/Contents/lib/python2.7/site-packages/gensim-0.8.7/py2.7.egg/gensim/models/word2vec.py”, line 312, in most_similar
raise ValueError(“cannot compute similarity with no input”)
ValueError: cannot compute similarity with no input

Answer 1

'..... / free ....- en.bin'中的单词具有

的形式

烯/ boardwalk_chapel EN / mutsu_munemitsu en / goffstown en / yaw_axis EN / john_e_fogarty_international_center EN / francielle_manoel_alberto 烯/ shinji_harada

所以，当你寻找'女孩'时，它就不存在了

Answer 2

为了扩大一点塞尔吉奥的答案，＆＃34;＆＃34;＆＃34;＆＃34;实际上是Freebase标识符，所以＆＃34; girl＆＃34;由/en/girl（对于freebase-vectors-skipgram1000-en.bin.gz）或其MID等效/m/05r655（对于freebase-vectors-skipgram1000.bin.gz）表示

https://www.freebase.com/m/05r655

https://www.freebase.com/en/girl

在gensim python中使用google word2vec .bin文件

2 个答案: