1. Paper title

Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation

2. link

https://www.aclweb.org/anthology/2020.acl-main.61.pdf

3. 摘要

Neural conversation models are known to generate appropriate but non-informative responses in general. A scenario where informativeness can be significantly enhanced is Conversing by Reading (CbR), where conversations take place with respect to a given external document. In previous work, the external document is utilized by (1) creating a contextaware document memory that integrates information from the document and the conversational context, and then (2) generating responses referring to the memory. In this paper, we propose to create the document memory with some anticipated responses in mind. This is achieved using a teacher-student framework. The teacher is given the external document, the context, and the ground-truth response, and learns how to build a response-aware document memory from three sources of information. The student learns to construct a response-anticipated document memory from the first two sources, and the teacher’s insight on memory creation. Empirical results show that our model outperforms the previous stateof-the-art for the CbR task.

4. 要解决什么问题

普通的聊天任务返回合理但无信息量的回答。
Cbr任务返回合理且包含信息的回答。
CbR的通常做法是（1）基于文本和问题生成document momery（2）生成指向momery的回答。

5. 作者的主要贡献

本文提供一种新的生成document momery的回答：
create the document memory with some anticipated responses in mind
先用document、context、response训练一个teacher。CbR模型作为student，根据document， context和teacher生成document momery。

[?] teacher-student framework

6. 得到了什么结果

在CbR任务上性能优于SOTA。

7. 关键字

对话与QA的结合。具有QA的基于指定文本的特点，和对话的交流的特点。