Dialogue management based on a hierarchical task structure
نویسندگان
چکیده
In conventional form-based dialogue manager, the task structure of a given task domain is built on E-form or flat slot structure, which some useful structure information of the task domain has been lost. This paper describes a hierarchical task structure model that is domain independent at least for a class of task domains. Based on the task structure model, a rule based dialogue management, which has some domain independent “conversational skill”, is presented.
منابع مشابه
Statistical Dialogue Management using Intention Dependency Graph
We present a method of statistical dialogue management using a directed intention dependency graph (IDG) in a partially observable Markov decision process (POMDP) framework. The transition probabilities in this model involve information derived from a hierarchical graph of intentions. In this way, we combine the deterministic graph structure of a conventional rule-based system with a statistica...
متن کاملThe Effects of Task Variation on the Accuracy and Complexity of Iranian EFL Learners’ Oral Performance
Task variation is an integrative method aiming at the importance of learner-to-learner interactions in a wide range of learning contexts and fostering authentic use of language and meaningful communication. This study investigated the impact of task variation on the accuracy and complexity of Iranian EFL learners’ oral speech. In so doing, 80 intermediate EFL learners, majoring English at the I...
متن کاملStudy of institutional Collaboration in the management Structure of the City Regions Case Study: Process of determining the city of Qazvin Growth boundaries.
This article is about the institutional collaboration in the management structure of a city-region. To achieve this purpose, corporate limits of Qazvin are studied as the city is becoming a region. The possible institutional cooperative in the centralist governmental structure is planned based on the new regionalism theory and its governance pattern, new institutionalism theory and its emphas...
متن کاملComposite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning
Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical fra...
متن کاملComposite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
Building a dialogue agent to fulfill complex tasks, such as travel planning, is challenging because the agent has to learn to collectively complete multiple subtasks. For example, the agent needs to reserve a hotel and book a flight so that there leaves enough time for commute between arrival and hotel check-in. This paper addresses this challenge by formulating the task in the mathematical fra...
متن کامل