qq_41648012的博客

# coding=utf-8from pyltp import SentenceSplitterfrom pyltp import Segmentorfrom pyltp import Postaggerfrom pyltp import NamedEntityRecognizerfrom pyltp import Parserfrom nltk import DependencyGr...

维基百科简体中文语料训练word2vec词向量步骤：1.下载维基百科中文语料2.使用工具从压缩包中抽取正文文本3.将繁体字转简体字4.分词5.训练模型6.测试模型1.下载维基百科中文语料语料下载地址：https://dumps.wikimedia.org/zhwiki/有不同时间段的下载地址，我们需要训练词向量，请选择包含articles.xml.bz2字段的链接（包含词...

#!/usr/bin/env python# -*- coding: utf-8 -*-# =============================================================================# Version: 2.75 (March 4, 2017)# Author: Giuseppe Attardi (attardi@di....

#include<bits/stdc++.h>using namespace std;typedef long long ll;const int INF=0x3f3f3f3f;const int MAX_M=1e4+5;const int MAX_K=30+5;const int MAX_N=1e6+5;struct node{ int id,k;//词...

#include<bits/stdc++.h>using namespace std;typedef long long ll;const int INF=0x3f3f3f3f;const int MAX_M=1e3+5;const int MAX_K=30+5;const int MAX_N=1e6+5;struct node{ int num; ...

import chardetimport jiebaimport gensimS1 = []S2 = []with open('C:\\Users\\28612\\Desktop\\news_sohusite_xml.dat', 'rb') as f: lines = f.readlines() ans = 0 for line in lines: ...