问如何计算短文本语料库的语义相似度？

EN

#Invoke libraries
from nltk import pos_tag, word_tokenize
from nltk.corpus import wordnet as wn


#Build functions to compute similarity
def ptb_to_wn(tag):    
    if tag.startswith('N'):
        return 'n' 
    if tag.startswith('V'):
        return 'v' 
    if tag.startswith('J'):
        return 'a' 
    if tag.startswith('R'):
        return 'r' 
    return None


def tagged_to_synset(word, tag):
    wn_tag = ptb_to_wn(tag)
    if wn_tag is None:
        return None 
    try:
        return wn.synsets(word, wn_tag)[0]
    except:
        return None


def sentence_similarity(s1, s2):    
    s1 = pos_tag(word_tokenize(s1))
    s2 = pos_tag(word_tokenize(s2)) 

    synsets1 = [tagged_to_synset(*tagged_word) for tagged_word in s1]
    synsets2 = [tagged_to_synset(*tagged_word) for tagged_word in s2]

    #suppress "none"
    synsets1 = [ss for ss in synsets1 if ss]
    synsets2 = [ss for ss in synsets2 if ss]

    score, count = 0.0, 0

    for synset in synsets1:
        best_score = max([synset.path_similarity(ss) for ss in synsets2])
        if best_score is not None:
            score += best_score
            count += 1

    # Average the values
    score /= count
    return score

#compute the symmetric sentence similarity
def symSentSim(s1, s2):
    sss_score = (sentence_similarity(s1, s2) + sentence_similarity(s2,s1)) / 2
    return (sss_score)

s1 = 'We rented a vehicle to drive to New York'
s2 = 'The car broke down on our jouney'            

s1tos2 = symSentSim(s1, s2)

print(s1tos2)
#0.142509920635