Alternatives and similar repositories for text-similarity

Users that are interested in text-similarity are comparing it to the libraries listed below

• supercoderhawk / DNN_CWS
  利用深度学习实现中文分词
  ☆63Updated 8 years ago
• shuyang790 / QA
  [Broken] A Chinese Question and Answer System
  ☆51Updated 9 years ago
• yesseecity / hanlp-python
  把之前 hanLP-python-flask 裡面的 hanLP 單獨分出來
  ☆59Updated 7 years ago
• hzhyhx1117 / word2vec-for-wiki
  A demo for processing wiki corpus by word2vec
  ☆51Updated 7 years ago
• jannson / wordmaker
  auto generate chinese words in huge text.
  ☆92Updated 10 years ago
• eecrazy / word2vec_chinese_annotation
  word2vec源码阅读，标记了中文注释
  ☆61Updated 8 years ago
• chenbjin / ASExtractor
  基于TextRank和WordNet的中英文单文档自动摘要
  ☆63Updated 9 years ago
• duanhongyi / genius
  a chinese segment base on crf
  ☆234Updated 6 years ago
• supercoderhawk / DeepLearning_NLP
  基于深度学习的自然语言处理库
  ☆159Updated 6 years ago
• apanly / proofreadv1
  中文文本自动纠错
  ☆85Updated 7 years ago
• mattzheng / LangueOne
  练习题︱基于今日头条开源数据的文本挖掘
  ☆84Updated 6 years ago
• yanghanxy / New-Word-Detection
  新词发现算法(NewWordDetection)
  ☆93Updated 4 years ago
• WenDesi / sentenceSimilarity
  基于gensim模块计算句子相似度
  ☆123Updated 9 years ago
• xccds / chinese_wordseg_keras
  基于深度学习的中文分词尝试
  ☆84Updated 9 years ago
• lihait / ExtractTopicSentence
  基于标题分类的主题句提取方法可描述为: 给定一篇新闻报道, 计算标题与新闻主题词集的相似度, 判断标题是否具有提示性。对于提示性标题,抽取新闻报道中与其最相似的句子作为主题句; 否则, 综合利用多种特征计算新闻报道中句子的重要性, 将得分最高的句子作为主题句。
  ☆40Updated 9 years ago
• HappyShadowWalker / ChineseTextClassify
  中文文本分类，使用搜狗文本分类语料库
  ☆125Updated 9 years ago
• LambdaWx / con_sentence
  卷积神经网络(CNN)应用于中文文本分析任务
  ☆34Updated 8 years ago
• Tony-Wang / YaYaNLP
  Pure python NLP toolkit
  ☆55Updated 9 years ago
• kenhenry / tensorflow-seq2seq-chatbot-zh
  tensorflow-seq2seq-chatbot-zh中文聊天机器人
  ☆27Updated 8 years ago
• fssqawj / SentenceSim
  中文短文句相似读
  ☆137Updated 7 years ago
• KG-book / EntityMining
  《实体数据挖掘与知识图谱构建》一书的代码和实验数据。
  ☆43Updated 9 years ago
• ustcdane / annotated_jieba
  对中文分词jieba (python版)的注解
  ☆93Updated 7 years ago
• hankcs / ID-CNN-CWS
  Source codes and corpora of paper "Iterated Dilated Convolutions for Chinese Word Segmentation"
  ☆135Updated 4 years ago
• izisong / new-words-discovery
  新词发现
  ☆66Updated 11 years ago
• eclipse-du / glove_py_model_load
  Loading the model from glove and computer word similarity & word clustering.
  ☆64Updated 11 years ago
• EternalFeather / Chatbot-Training-Corpus
  总结了一些可以用作聊天机器人训练实作的文字语聊，包含中英文不同语言
  ☆117Updated 7 years ago
• NoTwice1 / openkg-link
  常见中文知识图谱的链接
  ☆22Updated 8 years ago
• QuantumLiu / Neural-Headline-Generator-CN
  从门户网站爬取新闻的摘要-标题对使用seq2seq根据摘要生成标题
  ☆45Updated 8 years ago
• xingyuanbu / question-classification-cnn-rnn-attention
  针对百度知道电影问答数据的问题分类 question classification for zhidao.baidu.com in movie domain
  ☆25Updated 8 years ago
• chatopera / wikidata-corpus
  Train Wikidata with word2vec for word embedding tasks
  ☆123Updated 7 years ago