Beast code in Giters

uyru's starred repositories

Crawling zhihu, jobbole, lagou by Scrapy, and using Elasticsearch+Django to build a Search Engine website --- README_zh.md (including: implementation roadmap, distributed-crawler and coping with anti-crawling strategies).

Language:Python3700

NLPwebsite

自然语言处理网站标注系统，采用Django框架写的Python Web

Language:Python300

WEB_KG

爬取百度百科中文页面，抽取三元组信息，构建中文知识图谱

Language:Python91200

G-Reader

2018年机器阅读理解技术竞赛总结，国内外1000多支队伍中BLEU-4评分排名第6， ROUGE-L评分排名第14。（未ensemble，未嵌入训练好的词向量，无dropout）

Language:Python3100

word2vec-tensorflow

使用word2vec进行中文词向量的训练

Language:Python9100

Chinese-Word-Vectors

100+ Chinese Word Vectors 上百种预训练中文词向量

Language:PythonApache-2.01169900

word2vec-Finance

基于20W金融资讯训练得到的词向量

Language:Python2400

Min-Graph-Equipartition

Min-Graph Equipartition Problem with Simulated Annealing

Language:TeX100

Plagiarism-Detection

This is a utility to detect text plagiarism given 2 documents.

Language:Jupyter Notebook600

ProductAnalysis

抓取zol数据,django-haystack实现全文搜索,bokeh进行数据可视化,pandas进行数据分析

Language:Python3600

NLP_basis

这是我学习一个NLP教程【2019最新AI 自然语言处理之深度机器学习顶级项目实战课程】做的笔记与代码

Language:Python43100

ajaxSearch

模仿百度搜索栏制作一个简易的search demo

Language:Java1100

Domain_QA

限定域问答系统包括：自动构建知识库、问句检索、基于微信平台搭建问答系统。本项目所有代码已开源。用户通过简单配置，可以实现快速自动化搭建一个比较完备的领域知识库。另外，基于微信平台如何通过配置来搭建问答系统，具体操作见readme.txt

Language:Java7100

Measuring-Sentence-Similarity

The project aims to measure the similarity between sentences using Natural Language Processing tools like WordNet, NLTK. The Application works on semantic and syntactic features and then evaluates them using Machine Learning classifiers such as Logistic Regression and SVM ( SKlearn).

Language:Python400