这是人神大作业&实验室的活，我和gjr、swx、zzd四人组队刚这个东西，同时有nyl、jfk学长carry。

官网：https://stanfordnlp.github.io/coqa/

一些相关论文：

• CoQA[√, 我的批注]: CoQA: A Conversational Question Answering Challenge
• self-attention mechanism[√, 我的批注]: A Structured Self-attentive Sentence Embedding
• BiDAF[√, 我的批注, gjr的批注]: Bidirectional Attention Flow for Machine Comprehension
• Dataset Comparison[√, 我的批注]: A Qualitative Comparison of CoQA, SQuAD 2.0 and QuAC
• BiDAF++: QuAC : Question Answering in Context
• FlowQA[√, 我的批注, 我的ppt, gjr的批注]: Grasping Flow in History for Conversational Machine Comprehension
• BERT: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• DrQA[gjr的批注]: Reading Wikipedia to Answer Open-Domain Questions
• FusionNet[zzd的批注]: FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
• QANet[zzd的批注]: QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension

一些相关链接：

• TensorFlow LSTM 注意力机制图解

一些相关代码：

• CoQA evaluator
• BiDAF
• BiDAF++
• DrQA
• FlowQA