[文本语义相似] 基于Jaccard相似度

文本相似在问答系统中有很重要的应用，如基于知识的问答系统（Knowledge-based QA），基于文档的问答系统（Documen-based QA），以及基于FAQ的问答系统（Community-QA）等。像 对于问题的内容，需要进行相似度匹配，从而选择出与问题最接近，同时最合理的答案。本节介绍 基于Jaccard相似度。

算法描述：两句子分词后词语的交集中词语数与并集中词语数之比。

import os
import jieba
import pickle
import logging
import numpy as np

class StopWords(object):
    '''
    '''
    def __init__(self, stopwords_file=stopwords_file ):
        self.stopwords = set( [ word.strip() for word in open(stopwords_file, 'r') ] )
    
    def del_stopwords(self, words):
        return [ word for word in words if word not in self.stopwords ]
 
stop_word = StopWords()
 
# 是否分词、  及其停用词语
def _seg_word(words, jieba_flag=True, del_stopword=False):
    if jieba_flag:
        word_list = [stop_word.del_stopwords(words) if del_stopword else word for word in jieba.cut(words)] 
    else:
        word_list = [stop_word.del_stopwords(words) if del_stopword else word for word in words]
    return word_list


def sim_jaccard(s1, s2):
    """jaccard相似度"""
    s1, s2 = set(s1), set(s2)
    ret1 = s1.intersection(s2)  # 交集
    ret2 = s1.union(s2)  # 并集
    sim = 1.0 * len(ret1) / len(ret2)
    return sim


word1 = ['这是什么']
word2 = ['这个什么价钱']
word_sim = sim_jaccard( _seg_word(word1), _seg_word(word2) )

了解本专栏 订阅专栏 解锁全文