从gensim解释负面的Word2Vec相似性

Question

例如,我们使用gensim以下方法训练word2vec模型:

from gensim import corpora, models, similarities
from gensim.models.word2vec import Word2Vec

documents = ["Human machine interface for lab abc computer applications",
              "A survey of user opinion of computer system response time",
              "The EPS user interface management system",
              "System and human system engineering testing of EPS",
              "Relation of user perceived response time to error measurement",
              "The generation of random binary unordered trees",
              "The intersection graph of paths in trees",
              "Graph minors IV Widths of trees and well quasi ordering",
              "Graph minors A survey"]

texts = [[word for word in document.lower().split()] for document in documents]
w2v_model = Word2Vec(texts, size=500, window=5, min_count=1)

当我们查询单词之间的相似性时,我们发现负相似性得分:

>>> w2v_model.similarity('graph', 'computer')
0.046929569156789336
>>> w2v_model.similarity('graph', 'system')
0.063683518562347399
>>> w2v_model.similarity('survey', 'generation')
-0.040026775040430063
>>> w2v_model.similarity('graph', 'trees')
-0.0072684112978664561

我们如何解读负面分数？

如果它是余弦相似性不应该是范围[0,1]？

函数的上界和下界是Word2Vec.similarity(x,y)什么？文档中没有太多内容:https://radimrehurek.com/gensim/models/word2vec.html#gensim.models.word2vec.Word2Vec.similarity =(

看看Python包装器代码,也没有太多:https://github.com/RaRe-Technologies/gensim/blob/develop/gensim/models/word2vec.py#L1165

(如果可能的话,请指出.pyx实现相似性功能的代码.)

Answer 1

余弦相似度的范围为-1到1,与常规余弦波相同.

至于来源:

https://github.com/RaRe-Technologies/gensim/blob/ba1ce894a5192fc493a865c535202695bb3c0424/gensim/models/word2vec.py#L1511

def similarity(self, w1, w2):
    """
    Compute cosine similarity between two words.
    Example::
      >>> trained_model.similarity('woman', 'man')
      0.73723527
      >>> trained_model.similarity('woman', 'woman')
      1.0
    """
    return dot(matutils.unitvec(self[w1]), matutils.unitvec(self[w2])