写在前面
很多文本处理的问题都可以变成QA问题:
机器翻译machine translation: (What is the translation into French?)
命名实体识别named entity recognition (NER) :(What are the named entity tags in this sentence?)
词性识别part-of-speech tagging (POS) :(What are the part-of-speech tags?)
文本分类classification problems like sentiment analysis: (What is the sentiment?)
指代问题coreference resolution: (Who does ”their” refer to?)
这篇主要介绍QA问答系统中的动态记忆网络模型(Dynamic Memory Network),它是由4部分构成的,包括输入模块
、问题模块
、情景记忆模块
、输出模块
。