[文本语义相似] 基于ngram-tf-idf的余弦距离(gensim实现)

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bow的余弦距离计算相似度。

基于gensim的方式如下：
 

import os
import jieba
import pickle
import logging
import numpy as np
from gensim import corpora, models, similarities
 
 
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()

# gen 3-gram
def _list_3_ngram(words, n=3, m=2):
    pattern1 = re.compile(r'[0-9]')
    if len(words) < n:
        n = len(words)
    temp=[words[i - k:i] for k in range(m, n + 1) for i in range(k, len(words) + 1) ]
    return [item for item in temp if len(''.join(item).strip())>0 and len(pattern1.findall(''.join(item).strip()))==0]


# 是否分词、  及其停用词语
def _seg_word(words_list, 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)] for words in words_list]
    else:
        word_list = [[stop_word.del_stopwords(words) if del_stopword else word for word in words] for words in words_list]
    word_list = [['_'.join(i) for i in _list_3_ngram(words,n=3, m=2)] for words in words_list]
    return word_list
 
 
word_list = ['我爱北京天安门', '你好，在干嘛呢', '这个什么价钱']
word_list = _seg_word(word_list)
dic = corpora.Dictionary(word_list, prune_at=2000000) 
# 保存模型
dic_path = './bow.model'
dic.save( dic_path ) 
 
 
# 加载模型
dic = corpora.Dictionary.load(dic_path)  
 
# 构建tfidf模型
tfidf_model_path = './tfidf_model.model'
corpus_model= [dic.doc2bow(word) for word in word_list]
# 构建检索模型
tfidf_model = models.TfidfModel(corpus_model)
tfidf_model.save(tfidf_model_path)
corpus_tfidf = tfidf_model[corpus_model]
 
tfidf_index_path = './tfidf_index.model'
tfidf_index = similarities.MatrixSimilarity(corpus_tfidf)
tfidf_index.save(tfidf_index_path)
 
 
 
# 得到句子向量, 直接出检索结果(检索是基于word_list的)。
words = '你好，在干嘛呢'
word_bow = dic.doc2bow(_seg_word([words])[0])
word_tfidf = tfidf_model[word_bow]
tfidf_index[word_tfidf] 
 
 

了解本专栏 订阅专栏 解锁全文