Dialogue Control Research Articles

Learning to control listening-oriented dialogue using partially observable markov decision processes

Our aim is to build listening agents that attentively listen to their users and satisfy their desire to speak and have themselves heard. This article investigates how to automatically create a dialogue control component of such a listening agent. We collected a large number of listening-oriented dialogues with their user satisfaction ratings and used them to create a dialogue control component that satisfies users by means of Partially Observable Markov Decision Processes (POMDPs). Using a hybrid dialog controller where high-level dialog acts are chosen with a statistical policy and low-level slot values are populated by a wizard, we evaluated our dialogue control method in a Wizard-of-Oz experiment. The experimental results show that our POMDP-based method achieves significantly higher user satisfaction than other stochastic models, confirming the validity of our approach. This article is the first to verify, by using human users, the usefulness of POMDP-based dialogue control for improving user satisfaction in nontask-oriented dialogue systems.

Digitized Decision-Making System Research for Warehouse Planning Using Navigation Patterns Based on Visual LISP

To solve the problem of decision making for the planning and construction of warehouse area, a digitized decision-making system is developed based on AutoCAD with the development tools of Visual LISP in the paper. Using navigation patterns, a user is guided to accomplish the analysis, estimates, and the calculation of construction costs for various types of facilities planning and layout in warehouse area. The modular design method is utilized to build the system function model. The system includes analysis and estimates module, statistics and construction cost module and system management module. With the interface program between the system management module and the SQL Server database, the functional models are connected with the database dynamically. The man-machine interface established with Dialog Control Language is easy to use and accords with industry habits. All engineering parameters from national standards and industry standards are reliable and digitalized to establish parameter databases. The interface between AutoCAD software and the parameter databases is developed to call the data in the parameter databases from AutoCAD. Consequently, the efficiency and quality of warehouse planning can be improved. The system can also be extended to form a complete and standard digitized decision-making CAD system and improve the scientific rationality of the planning decisions for warehouse area.

Process-aware continuation management in web applications

Web applications are subject to an interaction challenge not found in other user interfaces: In addition to the widgets that web pages are built of, browsers provide further navigation features such as the Back and Forward buttons that are beyond the developer's control. Continuations have been suggested as a means to cope with the arbitrary navigation patterns that users may perform using these features. While an elegant solution in theory, continuations can incur a significant memory load in practice, and may offer more navigation options than business requirements mandate. We therefore propose a dialog control logic that augments the continuation approach with strategies for automatic elimination of continuations that will likely not be needed anymore, or whose invocation shall be prevented due to business requirements. This way, we aim to realize the benefits that continuations can provide to web applications, while ameliorating the drawbacks that they exhibit in practice.

Gymnasium Building Materials Performance-Type Research

Materials in sports building space plays not only a supporting role but also an important part of building exhibition. With the rise of intelligent and ecological buildings, as a building enclosure material properties and role will become more prominent. New advances in technology make material has been not just enclosure system, but with the external environment for building dialogue interface, visual, structure and control technique of bonding layer. How effectively function technology element integration in material artistic expressive force is the important thing in current material design.

Research and Study of Gear Class Components Parametrization Based on AutoCAD

For achieved gear class parts of design calculation and drawing of automation, the paper proposed the parameterization design concept ideas, Using Auto-CAD Visual LISP language and Dialog control language (DCL) to design dialog box, realized parameters input with dialog through programmatic, and design and calculation of gear parts, parameters, proofing and gear designs drawn with different structures, output complete automation computer aided system

Spatially-aware dialogue control using hierarchical reinforcement learning

This article addresses the problem of scalable optimization for spatially-aware dialogue systems. These kinds of systems must perceive, reason, and act about the spatial environment where they are embedded. We formulate the problem in terms of Semi-Markov Decision Processes and propose a hierarchical reinforcement learning approach to optimize subbehaviors rather than full behaviors. Because of the vast number of policies that are required to control the interaction in a dynamic environment (e.g., a dialogue system assisting a user to navigate in a building from one location to another), our learning approach is based on two stages: (a) the first stage learns low-level behavior, in advance; and (b) the second stage learns high-level behavior, in real time. For such a purpose we extend an existing algorithm in the literature of reinforcement learning in order to support reusable policies and therefore to perform fast learning. We argue that our learning approach makes the problem feasible, and we report on a novel reinforcement learning dialogue system that performs a joint optimization between dialogue and spatial behaviors. Our experiments, using simulated and real environments, are based on a text-based dialogue system for indoor navigation. Experimental results in a realistic environment reported an overall user satisfaction result of 89%, which suggests that our proposed approach is attractive for its application in real interactions as it combines fast learning with adaptive and reasonable behavior.

Dialogue control using partially observable Markov decision process

Dialogue control using partially observable Markov decision process

A multi-expert model for dialogue and behavior control of conversational robots and agents

This paper presents an intelligence model for conversational service robots. It employs modules called experts, each of which is specialized to execute certain kinds of tasks such as performing physical behaviors and engaging in dialogues. Some of the experts take charge in understanding human utterances and deciding robot utterances or actions. The model enables switching and canceling tasks based on recognized human intentions, as well as parallel execution of several tasks. This model specifies the interface that an expert must have, and any kind of expert can be employed if it conforms to the interface. This feature makes the model extensible.

A prototype for a conversational companion for reminiscing about images

This paper describes an initial prototype of the Companions project ( www.companions-project.org): the Senior Companion (SC), designed to be a platform to display novel approaches to: (1) The use of Information Extraction (IE) techniques to extract the content of incoming dialogue utterances after an ASR phase. (2) The conversion of the input to RDF form to allow the generation of new facts from existing ones, under the control of a Dialogue Manager (DM), that also has access to stored knowledge and knowledge accessed in real time from the web, all in RDF form. (3) A DM expressed as a stack and network virtual machine that models mixed initiative in dialogue control. (4) A tuned dialogue act detector based on corpus evidence. The prototype platform was evaluated, and we describe this; it is also designed to support more extensive forms of emotion detection carried by both speech and lexical content, as well as extended forms of machine learning. We describe preliminary studies and results for these, in particular a novel approach to enabling reinforcement learning for open dialogue systems through the detection of emotion in the speech signal and its deployment as a form of a learned DM, at a higher level than the DM virtual machine and able to direct the SC's responses to a more emotionally appropriate part of its repertoire.

Informal Elite Dialogue and Democratic Control in EU Foreign and Security Policy

As an academic artefact constitutionalism offers a reference frame for research on constitutional quality beyond the nation-state. The challenge for this research is to avoid methodological nationalism while acknowledging the institutions, principles and norms as the derivatives of ‘stateness’ which are enduring cosmopolitan elements of constitutionalism at the same time. The paper advances two arguments. First, if we are to ‘reconstruct democracy in Europe’, it is important to find out whether core elements of constitutionalism are still shared. Second, if we are to understand the quality of ‘European’ constitutionalism from a pluralist cosmopolitan perspective, it matters how the normative structure of meaning-in-use is enacted in 21st century Europe. The empirical access point for this research is social practices in inter-national relations. The paper therefore investigates social practices in the area of foreign and security policy, it elaborates on the concept of constitutionalism as a reference frame for studies of constitutional quality beyond the state, and turns to the CFSP setting, proposing that transnationalisation needs to be demonstrated with reference to shared normative baggage or cultural validation of norms. In sum findings and implications for research on democratic constitutionalism are explicated.

The RavenClaw dialog management framework

In this paper, we describe RavenClaw, a plan-based, task-independent dialog management framework. RavenClaw isolates the domain-specific aspects of the dialog control logic from domain-independent ...

Analysis of the oral interface in the interactive servicing systems. I

The oral technologies created a new type of the human-computer interaction. The oral servers and oral portals which implement a new model of human-computer communications may be studied using the methods of the queuing theory. Development of the analytical models to estimate some numerical characteristics of the human-computer one-channel dialogue such as the probability of successful dialogue, number of overinterrogations, and mean time of dialogue are the immediate subject matters of such studies. These characteristics may be used further to analyze operation of the entire queuing system that models the multichannel oral portal. The main parameters of the human-computer dialogue such as the probability of correct recognition of an element and the entire dialogue at overinterrogations and the time used for a dialogue element were considered. The parameters for estimation of the dialogue length were determined. A classification of the dialogue control algorithms at oral interaction of the client with the computer-aided information and servicing systems was developed. The algorithms were compared in terms of duration with regard for the desired reliability of recognition.

The RavenClaw dialog management framework: Architecture and systems

In this paper, we describe RavenClaw, a plan-based, task-independent dialog management framework. RavenClaw isolates the domain-specific aspects of the dialog control logic from domain-independent conversational skills, and in the process facilitates rapid development of mixed-initiative systems operating in complex, task-oriented domains. System developers can focus exclusively on describing the dialog task control logic, while a large number of domain-independent conversational skills such as error handling, timing and turn-taking are transparently supported and enforced by the RavenClaw dialog engine. To date, RavenClaw has been used to construct and deploy a large number of systems, spanning different domains and interaction styles, such as information access, guidance through procedures, command-and-control, medical diagnosis, etc. The framework has easily adapted to all of these domains, indicating a high degree of versatility and scalability.

Measuring Consumer Interactivity in Response to Campaigns Coupling Mobile and Television Media

ABSTRACT Consumers are increasingly using the mobile channel to be interactive with television programming and advertisements. To understand this emerging phenomena, we develop a model (the LOOP), conceptualizing the consumers interactivity when using their mobile phone to interact with television content. This model proposes new thinking regarding the role of the mobile channel in the consumer9s experience of the interactive television content. We define the consumer9s interactivity in terms of four characteristics: synchronicity, two-way dialogue, contingency, and user control. Based upon these characteristics, we use New Zealand and U.S. interactive television content related campaign data to develop five measures of campaign response effectiveness—Potential Audience Dialogue (PAD), Active Audience Dialogue (AAD), Interactive Audience Dialogue (IAD), Contingent Audience Loyalty (CAL), and Contingent Audience Wearout (CAW) We found similar response patterns across the tested New Zealand and U.S. campaigns, with more significant relationships emerging from interactive consumers who are loyal across campaigns.

A Reinforcement Learning approach to evaluating state representations in spoken dialogue systems

Although dialogue systems have been an area of research for decades, finding accurate ways of evaluating different systems is still a very active subfield since many leading methods, such as task completion rate or user satisfaction, capture different aspects of the end-to-end human–computer dialogue interaction. In this work, we step back the focus from the complete evaluation of a dialogue system to presenting metrics for evaluating one internal component of a dialogue system: its dialogue manager. Specifically, we investigate how to create and evaluate the best state space representations for a Reinforcement Learning model to learn an optimal dialogue control strategy. We present three metrics for evaluating the impact of different state models and demonstrate their use on the domain of a spoken dialogue tutoring system by comparing the relative utility of adding three features to a model of user, or student, state. The motivation for this work is that if one knows which features are best to use, one can construct a better dialogue manager, and thus better performing dialogue systems.

A Highly Reusable Code Assignment Approach with Modified Busy Tone Signaling for CDMA-Based Ad Hoc Networks

Medium access control (MAC) protocol is among the most active topics of research in ad hoc networks. With the CDMA-based MAC protocol the code allocation plays an important role and has significant impact on the protocol performance. In this paper, we propose a distributed CDMA code assignment protocol for the mobile ad hoc networks (MANETs). The protocol is mainly composed of (1) a modified busy tone signaling mechanism that protects on-going data transmission as well as distributes code usage information, and (2) a set of specially designed code selection rules that work by taking into consideration whether relevant nodes are in the transmitting or receiving state. By combining the two proposed schemes with the conventional request-to-send (RTS)/clear-to-send (CTS) dialogue and power control mechanism, our protocol is able to increase CDMA code reusability. The simulation results indicate that the proposed protocol indeed performs better than the static and dynamic code assignment methods (either with or without power control) in terms of successful transmission rate and successful code assignment rate. And instead of sending continuously, the proposed modified busy tone mechanism only issues busy tone signal in randomly selected cycles, which may save battery energy as compared to conventional busy tone implementations. Moreover, the proposed code selection rules and the modified busy tone signaling may also be integrated into existing MAC protocols, either separately or in combination.

Multiple utterance prediction based on a tree structure of dialogue states

A problem of spoken dialogue systems is that recognition errors increase when the recognition‐word vocabulary is large. To solve the problem, we propose a method to predict a user’s utterances by recognizing prediction sentences of each dialogue state. The method can judge whether the user’s utterance is within the range of prediction using decoders based on a prediction sentence and a large word vocabulary. However, the conventional method performs processing to lead in a prediction frequently when a topic changes because even an utterance within a domain is treated as an utterance of the prediction outside. In this study, we propose a new method using multiple predictions by performing recognition based on all prediction sentences in a domain. The proposed method produces a tree structure for dialogue states in a domain and regards child nodes of an arbitrary node as within the range of prediction. We conducted experiments for 451 utterances of 15 dialogues by ten persons using the university guide system. As a result, recognition accuracy of prediction sentences was 97.7% and the judgment accuracy of utterance predictions was 88.2%; high performance was obtained using the proposed method. Results demonstrate that it is possible to perform flexible dialogue control.

Adaptation and user expertise modelling in AthosMail

This article describes the User Model component of AthosMail, a speech-based interactive e-mail application developed in the context of the EU project DUMAS. The focus is on the system’s adaptive capabilities and user expertise modelling, exemplified through the User Model parameters dealing with initiative and explicitness of the system responses. The purpose of the conducted research was to investigate how the users could interact with a system in a more natural way, and the two aspects that mainly influence the system’s interaction capabilities, and thus the naturalness of the dialogue as a whole, are considered to be the dialogue control and the amount of information provided to the user. The User Model produces recommendations of the system’s appropriate reaction depending on the user’s observed competence level, monitored and computed on the basis of the user’s interaction with the system. The article also discusses methods for the evaluation of adaptive user models and presents results from the AthosMail evaluation.

Modelling of an interactive system with an agent-based architecture using Petri nets, application of the method to the supervision of a transport system

This article presents an original method using high level Petri nets for the specification and design of interactive systems. We suggest an agent oriented architecture based on the classic components of an interactive application (application, dialogue control, interface with the application). Our approach is validated via the specification and design of a human–machine interface used in the supervision of a land-based transport system (bus/tramway).

A Dialogue Control Model Based on Ambiguity Evaluation of Users’ Instructions and Stochastic Representation of Experiences

To operate in everyday environments, robots much accomplish complex tasks following often mbiguous and uncertain instructions, mainly through advanced inference or recognition. We focus on an intelligent human-robot interaction framework that reduces the burden of the user. Robots compensate for ambiguities by active sensing and dialogue control through questions and suggestions to users. Robots also use experience to reduce the user’s burden. We propose a criterion for ambiguity evaluation of user instructions, stochastic representation of personal experiences and a dialogue control model for accomplishing tasks in complex environments. We demonstrate the feasibility of our proposal in demonstrate experiment where a robot searches for an object in disorganized work space with ambiguous instructions.