An Online Generated Transducer to Increase Dialog Manager Coverage
نویسندگان
چکیده
This paper presents a new approach for dynamically increasing the coverage of a Statistical Dialog Manager. A Stochastic Finite-State Transducer for dialog management is estimated using a dialog simulator. This corpusbased model can cover most typical user behavior; however, sometimes unexpected situations may arise. Whenever these situations occur, the Dialog Manager model has no information to determine the next action. To deal with this problem, an Online Dialog Simulator is used in order to obtain synthetic dialogs for re-estimating the model and allowing the Dialog Manager to continue the dialog. This approach has been evaluated with real users in a sport facilities booking task.
منابع مشابه
Mon .P1d .01 13:30–15:30 Portability of Semantic Annotations for Fast Development of Dialogue Corpora
This paper presents a new approach for dynamically increasing the coverage of a Statistical Dialog Manager. A Stochastic Finite-State Transducer for dialog management is estimated using a dialog simulator. This corpusbased model can cover most typical user behavior; however, sometimes unexpected situations may arise. Whenever these situations occur, the Dialog Manager model has no information t...
متن کاملA stochastic finite-state transducer approach to spoken dialog management
In this paper, we present an approach to spoken dialog management based on the use of a Stochastic Finite-State Transducer estimated from a dialog corpus. The states of the Stochastic Finite-State Transducer represent the dialog states, the input alphabet includes all the possible user utterances, without considering specific values, and the set of system answers constitutes the output alphabet...
متن کاملDialog management using weighted finite-state transducers
We are aiming to construct an expandable and adaptable dialog system which handles multiple tasks and senses users’ intention via multiple modalities. A flexible platform to integrate different dialog strategies and modalities is indispensable for this purpose. In this paper, we propose an efficient approach to manage a dialog system using a weighted finitestate transducer (WFST) in which users...
متن کاملRecent advances in WFST-based dialog system
To construct an expandable and adaptable dialog system which handles multiple tasks, we proposed a dialog system using a weighted finite-state transducer (WFST) in which users concept and system action tags are input and output of the transducer, respectively. To test the potential of the WFSTbased dialog management (DM) platform using statistical DM models, we constructed a dialog system using...
متن کاملUsing Wizard-of-Oz simulations to bootstrap Reinforcement - Learning based dialog management systems
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 handcraf...
متن کامل