Data Augmentation in NLPWord SubstitutionSynonym-based substitutionWord embedding substitutionMasked language modelTF-IDF-based word substitutionThe basic idea is that words with a low TF-IDF score ar

CS224n学习笔记CS224n: Natural Language Processing with Deep Learning代码及笔记在 https://github.com/AngusMonroe/CS224n 持续更新

pip install stanfordcorenlp去官网下载CoreNLP解压CoreNLP，得到stanford-corenlp-4.2.0unzip stanford-corenlp-latest.zip简单实用示例：>>> from stanfordcorenlp import StanfordCoreNLP>>> nlp = StanfordCore

Redis数据类型String:二进制安全,可以包含任何数据Hash:一个键值(key=>value)对集合List:简单的字符串列表Set:string类型的无序集合Zset:每个元素都会关联一个double类型的分数,redis通过分数来为集合中的成员进行从小到大的排序Redis基本命令Key:set, get, deleteHash: hmset, ...