1. Paper title

End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2

2. link

https://www.aclweb.org/anthology/2020.acl-main.54.pdf

3. 摘要

The goal-oriented dialogue system needs to be optimized for tracking the dialogue flow and carrying out an effective conversation under various situations to meet the user goal. The traditional approach to building such a dialogue system is to take a pipelined modular architecture, where its modules are optimized individually. However, such an optimization scheme does not necessarily yield an overall performance improvement of the whole system. On the other hand, end-to-end dialogue systems with monolithic neural architecture are often trained only with input-output utterances, without taking into account the entire annotations available in the corpus. This scheme makes it difficult for goal-oriented dialogues where the system needs to be integrated with external systems or to provide interpretable information about why the system generated a particular response. In this paper, we present an end-to-end neural architecture for dialogue systems that addresses both challenges above. Our dialogue system achieved the success rate of 68.32%, the language understanding score of 4.149, and the response appropriateness score of 4.287 in human evaluations, which ranked the system at the top position in the end-to-end multi-domain dialogue system task in the 8th dialogue systems technology challenge (DSTC8).

monolithic neural architecture：整体神经架构
utterances：话语
annotations：注解

4. 要解决什么问题

任务型对话系统有两种架构。
pipeline架构对各个部分分别优化而不能保证整体性能最优。
end-to-end架构直接使用输入输出来训练整体神经架构，难以与其它系统集成，或者提供可解释信息。

5. 作者的主要贡献

提供一种能同时解决以上两个问题的end-to-end架构。

6. 得到了什么结果

DSTC8比赛上第一名。
成功率：68.32%， language understanding score：4.149， response appropriateness score：4.287

7. 关键字

任务型对话系统