VIP内容

题目: A Survey on Dialog Management: Recent Advances and Challenges

摘要:

对话管理(DM)是面向任务的对话系统的一个重要组成部分。给定对话历史记录,DM预测对话状态并决定对话代理应该采取的下一步操作。近年来,对话策略学习被广泛地定义为一种强化学习(RL)问题,越来越多的研究集中在DM的适用性上。在本文中,综述了DM的三个关键主题的最新进展和挑战:

  • 提高模型可扩展性,方便对话系统在新场景下建模;
  • 处理对话策略学习的数据稀缺性问题;
  • 提高培训效率,实现更好的任务完成绩效。

相信这项调查可以为未来对话管理的研究提供一些启示。

成为VIP会员查看完整内容
0
20

最新论文

Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build two large-scale medical dialogue datasets: MedDialog-EN and MedDialog-CN. MedDialog-EN is an English dataset containing 0.3 million conversations between patients and doctors and 0.5 million utterances. MedDialog-CN is an Chinese dataset containing 1.1 million conversations and 4 million utterances. To our best knowledge, MedDialog-(EN,CN) are the largest medical dialogue datasets to date. The dataset is available at https://github.com/UCSD-AI4H/Medical-Dialogue-System

0
0
下载
预览
父主题
Top