CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
A Teacher-Student Framework for Maintainable Dialog Manager
Wang, Weikang1; Zhang, Jiajun1; Zhang, Han2; Hwang, Mei-Yuh2; Zong, Chengqing1; Li, Zhifei2
2018
会议名称EMNLP
会议日期2018-11
会议地点Brussels, Belgium
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.

文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/23199
专题模式识别国家重点实验室_自然语言处理
作者单位1.中国科学院自动化研究所
2.出门问问
第一作者单位中国科学院自动化研究所
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],2018.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wang, Weikang]的文章
[Zhang, Jiajun]的文章
[Zhang, Han]的文章
百度学术
百度学术中相似的文章
[Wang, Weikang]的文章
[Zhang, Jiajun]的文章
[Zhang, Han]的文章
必应学术
必应学术中相似的文章
[Wang, Weikang]的文章
[Zhang, Jiajun]的文章
[Zhang, Han]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。