Dialogue Manager for Spoken Dialogue System: Review
نویسندگان
چکیده
A Spoken Dialogue System provide is a computer system able to converse with human with human voice. Dialogue Manager is a component of SDS that manages state of dialogue and dialogue strategy. This report presents the literature survey based on DM. The papers are based on various components of DM. The components of DM are dialogue representation, belief state representation, policy optimization and reinforcement learning, reward function and user simulator. The papers based on multi domain SDS and application of SDS is also presented. The different software required to build SDS are reviewed. Future direction and challenges of SDS are also discussed in report. Virtually all current SDSs are designed to operate in either a specific carefully defined domain such as restaurant information and appointment booking, or they have very limited conversational ability such as in Siri and Google Now. However, if voice is to become a significant input modality for accessing web-based information and services, then techniques will be needed to enable conversational SDSs to operate within open domains. Thus there is a need to build SDS for open domain. My research objective is to build DM for SDS to cope with open domain considering the possible interaction between computer and human. Index Terms – Reinforcement Learning, Dialogue Manager, Belief representation. __________________________________________________*****_________________________________________________
منابع مشابه
On-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملEfficient Spoken Dialogue Domain Representation and Interpretation
We provide a detailed look on the functioning of the OwlSpeak Spoken Dialogue Manager, which is part of the EU-funded project ATRACO. OwlSpeak interprets Spoken Dialogue Ontologies and on this basis generates VoiceXML dialogue snippets. The dialogue snippets can be interpreted by all speech servers that provide VoiceXML support and therefore make the dialogue management independent from the hos...
متن کاملResults from an Evaluation of a Dialogue Manager
We give the results from an evaluation of the dialogue manager of a developing, Slovenian and Croatian spoken dialogue system for weather-information retrieval. The results are based on two Wizard-of-Oz experiments and the application of the PARADISE evaluation framework. The only difference between both experiment settings is in the dialogue-management manner, i.e., while in the first experime...
متن کاملExample and Situation Based Dialog Management for Spoken Dialogue System
In this demonstration, we present POSSDM (POSTECH Situation based Dialogue Manager) for a spoken dialogue system using a new example and situation based dialogue management techniques for effective generation of appropriate system responses. Spoken dialogue system should generate cooperative responses to smoothly lead the dialogue with users. We introduce a new dialogue management technique inc...
متن کاملSpoken Dialogue Management Using Probabilistic Reasoning
Spoken dialogue managers have benefited from stochastic planners such as MDPs. However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a POMDP-style approach to generate dialogue strategies by inverting the notion of dialogue state; the state represents the user's intentions, rather than the system state. We compare the performance of MDP and POMDP dialogue manage...
متن کامل