5
我使用word2vec來表示一個小短語(3到4個字)作爲一個獨特的矢量,要麼通過添加每個單詞嵌入或通過計算字嵌入的平均值。word2vec,總和或平均單詞嵌入?
從我做過的實驗中總會得到相同的餘弦相似度。我懷疑它與word2vec生成的單詞向量在訓練之後是否與單位長度(歐幾里得範數)相同?或者我在代碼中有一個BUG,或者我錯過了一些東西。
下面是代碼:
import numpy as np
from nltk import PunktWordTokenizer
from gensim.models import Word2Vec
from numpy.linalg import norm
from scipy.spatial.distance import cosine
def pattern2vector(tokens, word2vec, AVG=False):
pattern_vector = np.zeros(word2vec.layer1_size)
n_words = 0
if len(tokens) > 1:
for t in tokens:
try:
vector = word2vec[t.strip()]
pattern_vector = np.add(pattern_vector,vector)
n_words += 1
except KeyError, e:
continue
if AVG is True:
pattern_vector = np.divide(pattern_vector,n_words)
elif len(tokens) == 1:
try:
pattern_vector = word2vec[tokens[0].strip()]
except KeyError:
pass
return pattern_vector
def main():
print "Loading word2vec model ...\n"
word2vecmodelpath = "/data/word2vec/vectors_200.bin"
word2vec = Word2Vec.load_word2vec_format(word2vecmodelpath, binary=True)
pattern_1 = 'founder and ceo'
pattern_2 = 'co-founder and former chairman'
tokens_1 = PunktWordTokenizer().tokenize(pattern_1)
tokens_2 = PunktWordTokenizer().tokenize(pattern_2)
print "vec1", tokens_1
print "vec2", tokens_2
p1 = pattern2vector(tokens_1, word2vec, False)
p2 = pattern2vector(tokens_2, word2vec, False)
print "\nSUM"
print "dot(vec1,vec2)", np.dot(p1,p2)
print "norm(p1)", norm(p1)
print "norm(p2)", norm(p2)
print "dot((norm)vec1,norm(vec2))", np.dot(norm(p1),norm(p2))
print "cosine(vec1,vec2)", np.divide(np.dot(p1,p2),np.dot(norm(p1),norm(p2)))
print "\n"
print "AVG"
p1 = pattern2vector(tokens_1, word2vec, True)
p2 = pattern2vector(tokens_2, word2vec, True)
print "dot(vec1,vec2)", np.dot(p1,p2)
print "norm(p1)", norm(p1)
print "norm(p2)", norm(p2)
print "dot(norm(vec1),norm(vec2))", np.dot(norm(p1),norm(p2))
print "cosine(vec1,vec2)", np.divide(np.dot(p1,p2),np.dot(norm(p1),norm(p2)))
if __name__ == "__main__":
main()
這裏是輸出:
Loading word2vec model ...
Dimensions 200
vec1 ['founder', 'and', 'ceo']
vec2 ['co-founder', 'and', 'former', 'chairman']
SUM
dot(vec1,vec2) 5.4008677771
norm(p1) 2.19382594282
norm(p2) 2.87226958166
dot((norm)vec1,norm(vec2)) 6.30125952303
cosine(vec1,vec2) 0.857109242583
AVG
dot(vec1,vec2) 0.450072314758
norm(p1) 0.731275314273
norm(p2) 0.718067395416
dot(norm(vec1),norm(vec2)) 0.525104960252
cosine(vec1,vec2) 0.857109242583
我使用的是這裏Cosine Similarity (Wikipedia)定義的餘弦相似度。規範和點積的值確實不同。
任何人都可以解釋爲什麼餘弦相同嗎?
謝謝 大衛
謝謝你的回答。 我發現這個頁面,它解釋了餘弦相似性,Pearson相關性和OLS係數都可以看作是內積(即位置和比例等)的變體。 http://brenocon.com/blog/2012/03/cosine-similarity-pearson-correlation-and-ols-coefficients/ –