A Teacher-Student Framework for Maintainable Dialog Manager | |
Wang, Weikang1![]() ![]() ![]() | |
2018 | |
会议日期 | 2018-11 |
会议地点 | Brussels, Belgium |
英文摘要 | Reinforcement learning (RL) is an attractive solution for task-oriented dialog systems. However, extending RL-based systems to handle new intents and slots requires a system redesign. The high maintenance cost makes it difficult to apply RL methods to practical systems on a large scale. To address this issue, we propose a practical teacherstudent framework to extend RL-based dialog systems without retraining from scratch. Specifically, the “student” is an extended dialog manager based on a new ontology, and the “teacher” is existing resources used for guiding the learning process of the “student”. By specifying constraints held in the new dialog manager, we transfer knowledge of the “teacher” to the “student” without additional resources. Experiments show that the performance of the extended system is comparable to the system trained from scratch. More importantly, the proposed framework makes no assumption about the unsupported intents and slots, which makes it possible to improve RL-based systems incrementally. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23199] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_自然语言处理团队 |
作者单位 | 1.中国科学院自动化研究所 2.出门问问 |
推荐引用方式 GB/T 7714 | Wang, Weikang,Zhang, Jiajun,Zhang, Han,et al. A Teacher-Student Framework for Maintainable Dialog Manager[C]. 见:. Brussels, Belgium. 2018-11. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论