fighting41love / NLP_Corpus_PlanLinks
☆37Updated 6 years ago
Alternatives and similar repositories for NLP_Corpus_Plan
Users that are interested in NLP_Corpus_Plan are comparing it to the libraries listed below
Sorting:
- ZhidaoChatbot, a chatbot that can be an expert on the common questions like why,how,when,who,what based on the online question-answer web…☆42Updated 6 years ago
- self complemented SpellCorrection based pinyin similairity, edit distance ,基于拼音相似度与编辑距离的查询纠错。☆83Updated 3 years ago
- worddict crawler and transfer for sougpuinput wordict , 搜狗输入法词库抓取与格式转换☆25Updated 7 years ago
- 中文、分词、词表、核心词典、事件词表、停用词、敏感词、问答、问答数据、知识图谱、文本语料。☆167Updated 3 years ago
- 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
- self complement of baike knowledge base info-box extraction by online analysis.基于互动百科,百度百科,搜狗百科的词条infobox结构化信息抽取,百科知识的融合☆35Updated 7 years ago
- 发现新词 无监督词库生成 医学词库生成 发现未登录词☆78Updated 4 years ago
- Self complemented Pinyin2Chinese demo use algorithms including Trie and HMM model , 基于隐马尔科夫模型与Trie树的拼音切分与拼音转中文的简单demo实现。☆86Updated 7 years ago
- 中文新词发现算法PNW 算法,可以识别任意长度的新词。☆15Updated 2 years ago
- 用tf实现各种文本分类模型,并且封装restful接口,可以直接工程化☆32Updated 6 years ago
- 智能客服☆106Updated 6 years ago
- 文本对关系比较 - 语义相似度、字面相似度、文本蕴含等等☆55Updated 5 years ago
- self summary after attending CCL2018 (全国计算语言学学术会议), CCL2018参会总结,包括会议论文下载脚本,会议前言技术报告下载,以及个人的一点总结.☆27Updated 6 years ago
- 转换搜狗拼音词库为txt文件☆50Updated 7 years ago
- chinese anti semantic word search interface based on dict crawled from online resources, ChineseAntiword,针对中文词语的反义词查询接口☆59Updated 6 years ago
- 🤖️ 聊天机器人——夫子的「自然语言理解」模块☆90Updated 2 years ago
- 中文文本自动纠错☆85Updated 7 years ago
- 新词发现算法(NewWordDetection)☆62Updated 7 years ago
- 汉字字符特征提取工具,可以提取出字符中的字音(声母、韵母、声调)、字形(偏旁、部首)、四角编码等特征,同时可作为tensor输入到模型☆136Updated 5 years ago
- 练习题︱基于今日头条开源数据的文本挖掘☆84Updated 6 years ago
- 利用文本分析算法和Python脚本,自动纠正word中的英语单词拼写错误☆47Updated 6 years ago
- Code lab for NLP. Including doc2txt,tf-idf,cnn,text classify,hmm cws,crf ner.☆42Updated 7 years ago
- self complemented WeiboIndexSpyder based on Selenium ,新浪微博指数(微指数)采集,包括综合指数,移动端指数,PC端指数☆31Updated 7 years ago
- 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
- Word similarity computation based on Tongyici Cilin☆120Updated 8 years ago
- Code for chinese error detection module, using n-gram and bi-lstm☆135Updated 6 years ago
- This is a corpus of Chinese abbreviation, including negative full forms.☆196Updated 4 years ago
- Train Wikidata with word2vec for word embedding tasks☆123Updated 7 years ago
- 语义理解/口语理解,项目包含有词法分析:中文分词、词性标注、命名实体识别;口语理解:领域分类、槽填充、意图识别。☆182Updated 6 years ago
- 微调预训练语言模型(BERT、Roberta、XLBert等),用于计算两个文本之间的相似度(通过句子对分类任务转换),适用于中文文本☆89Updated 5 years ago