paper-with-me

홈 › Papers

Affordable On-line Dialogue Policy Learning

2017-09-01 · EMNLP 2017 9 · Cheng Chang, Runzhe Yang, Lu Chen, Xiang Zhou, Kai Yu

The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, efficient and economical. But in reality, due to the scarcity of real interaction data, the dialogue system usually grows slowly. Besides, the poor initial dialogue policy easily leads to bad user experience and incurs a failure of attracting users to contribute training data, so that the learning process is unsustainable. To accurately depict this, two quantitative metrics are proposed to assess safety and efficiency issues. For solving the unsustainable learning problem, we proposed a complete companion teaching framework incorporating the guidance from the human teacher. Since the human teaching is expensive, we compared various teaching schemes answering the question how and when to teach, to economically utilize teaching budget, so that make the online learning process affordable.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue Management

Similar Papers 제목 키워드 기반

Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning

2020-12-28 · Yangyang Zhao, Zhenyu Wang, Zhenhua Huang

Dialogue policy learning based on reinforcement learning is difficult to be applied to real users to train dialogue agents from scratch because of the high cost. User simulators, which choose random user goals for the di…

Integrating Pretrained Language Model for Dialogue Policy Learning

2021-11-02 · Hongru Wang, Huimin Wang, Zezhong Wang, Kam-Fai Wong

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward can be very sparse for it is usually only…

Language ModelingLanguage ModellingmodelReinforcement Learning (RL)

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

2021-02-20 · EMNLP 2021 11 · Haoming Jiang, Bo Dai, Mengjiao Yang, Tuo Zhao 외

Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interact…

Model-based Reinforcement LearningOff-policy evaluationreinforcement-learningReinforcement Learning+2

Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game

2017-08-01 · WS 2017 8 · Ramesh Manuvinakurike, David DeVault, Kallirroi Georgila

We apply Reinforcement Learning (RL) to the problem of incremental dialogue policy learning in the context of a fast-paced dialogue game. We compare the policy learned by RL with a high-performance baseline policy which …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Spoken Dialogue Systems

Affordable Generative Agents

2024-02-03 · Yangbin Yu, Qin Zhang, Junyou Li, Qiang Fu 외

The emergence of large language models (LLMs) has significantly advanced the simulation of believable interactive agents. However, the substantial cost on maintaining the prolonged agent interactions poses challenge over…