Using Wizard-of-Oz simulations to bootstrap Reinforcement - Learning based dialog management systems

نویسندگان

  • Jason D. Williams
  • Steve J. Young
چکیده

This paper describes a method for “bootstrapping” a Reinforcement Learningbased dialog manager using a Wizard-ofOz trial. The state space and action set are discovered through the annotation, and an initial policy is generated using a Supervised Learning algorithm. The method is tested and shown to create an initial policy which performs significantly better and with less effort than a handcrafted policy, which can be generated using a small number of dialogs.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Behavior models for learning and receptionist dialogs

We present a dialog model for identifying persons, learning person names, and associated face IDs in a receptionist dialog. The proposed model allows a decomposition of the main dialog task into separate dialog behaviors which can be implemented separately and allow a mixture of handcrafted models and dialog strategies trained with reinforcement learning. The dialog model was implemented on our...

متن کامل

Learning human multimodal dialogue strategies

We investigate the use of different machine learning methods in combination with feature selection techniques to explore human multimodal dialogue strategies and the use of those strategies for automated dialogue systems. We learn policies from data collected in a Wizardof-Oz study where different human ‘wizards’ decide whether to ask a clarification request in a multimodal manner or else to us...

متن کامل

Learning human multimodal dialogue strategies

We investigate the use of different machine learning methods in combination with feature selection techniques to explore human multimodal dialogue strategies and the use of those strategies for automated dialogue systems. We learn policies from data collected in a Wizardof-Oz study where different human ‘wizards’ decide whether to ask a clarification request in a multimodal manner or else to us...

متن کامل

Rapid simulation-driven reinforcement learning of multimodal dialog strategies in human-robot interaction

In this work we propose a procedure model for rapid automatic strategy learning in multimodal dialogs. Our approach is tailored for typical task-oriented human-robot dialog interactions, with no prior knowledge about the expected user and system dynamics being present. For such scenarios, we propose the use of stochastic dialog simulation for strategy learning, where the user and system error m...

متن کامل

Wizard of Oz Method for Learning Dialog Agents

This paper describes a framework to construct interface agents with example dialogs based on the tasks by the machine learning technology. The Wizard of Oz method is used to collect example dialogs, and a finite state machine-based model is used for the dialog model. We implemented a Web-based system which includes these functions, and empirically examined the system which treats with a guide t...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003