DFKI Approach to Dialogue Management Norbert Reithinger, Elsa Pecourt, Markus Löckelt

Slides:



Advertisements
Similar presentations
MicroKernel Pattern Presented by Sahibzada Sami ud din Kashif Khurshid.
Advertisements

GMD German National Research Center for Information Technology Darmstadt University of Technology Perspectives and Priorities for Digital Libraries Research.
Technical and design issues in implementation Dr. Mohamed Ally Director and Professor Centre for Distance Education Athabasca University Canada New Zealand.
Map of Human Computer Interaction
Co-funded by the European Union Semantic CMS Community IKS impact on DFKI research Final Review Luxembourg March 13/14, 2013 Tilman Becker DFKI GmbH.
From Model-based to Model-driven Design of User Interfaces.
Manuela Veloso, Anthony Stentz, Alexander Rudnicky Brett Browning, M. Bernardine Dias Faculty Thomas Harris, Brenna Argall, Gil Jones Satanjeev Banerjee.
© Löckelt, Becker, Pfleger, Alexandersson; DFKI Edilog 2002 Workshop Jan Alexandersson (Tilman Becker, Markus Löckelt, Norbert Pfleger) German Research.
Empirical and Data-Driven Models of Multimodality Advanced Methods for Multimodal Communication Computational Models of Multimodality Adequate.
MediaHub: An Intelligent Multimedia Distributed Hub Student: Glenn Campbell Supervisors: Dr. Tom Lunney Prof. Paul Mc Kevitt School of Computing and Intelligent.
Dialogue in Intelligent Tutoring Systems Dialogs on Dialogs Reading Group CMU, November 2002.
I1-[OntoSpace] Ontologies for Spatial Communication John Bateman, Kerstin Fischer, Reinhard Moratz Scott Farrar, Thora Tenbrink.
Media Coordination in SmartKom Norbert Reithinger Dagstuhl Seminar “Coordination and Fusion in Multimodal Interaction” Deutsches Forschungszentrum für.
LE TRINDIKIT A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Knowledge Acquisitioning. Definition The transfer and transformation of potential problem solving expertise from some knowledge source to a program.
Sharing Knowledge in Adaptive Learning Systems Miloš Kravčík Dragan Gašević Fraunhofer FIT, GermanySimon Fraser University, Canada
Industrial Ontologies Group Oleksiy Khriyenko, Vagan Terziyan INDIN´04: 24th – 26th June, 2004, Berlin, Germany OntoSmartResource: An Industrial Resource.
© 2005 Prentice Hall12-1 Stumpf and Teague Object-Oriented Systems Analysis and Design with UML.
Multimodal Interaction. Modalities vs Media Modalities are ways of encoding information e.g. graphics Media are instantiations of modalities e.g. a particular.
Research about dialogue and dialogue systems and the department of linguistics goal: –develop theories about human dialogue which can be used when building.
Application architectures
TrindiKit A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
WP1 UGOT demos 2nd year review Saarbrucken Mar 2006.
Community Manager A Dynamic Collaboration Solution on Heterogeneous Environment Hyeonsook Kim  2006 CUS. All rights reserved.
Cloud based linked data platform for Structural Engineering Experiment Xiaohui Zhang
Web Application Architecture: multi-tier (2-tier, 3-tier) & mvc
Mobile Multimodal Applications. Dr. Roman Englert, Gregor Glass March 23 rd, 2006.
Katanosh Morovat.   This concept is a formal approach for identifying the rules that encapsulate the structure, constraint, and control of the operation.
GUI: Specifying Complete User Interaction Soft computing Laboratory Yonsei University October 25, 2004.
Steps Toward an AGI Roadmap Włodek Duch ( Google: W. Duch) AGI, Memphis, 1-2 March 2007 Roadmaps: A Ten Year Roadmap to Machines with Common Sense (Push.
INDIN' Perth, Australia Multi-Agent Based Information Access Services for Condition Monitoring in Process Automation Teppo Pirttioja 1, Antti.
Computer Science CPSC 322 Lecture 3 AI Applications 1.
Experiments on Building Language Resources for Multi-Modal Dialogue Systems Goals identification of a methodology for adapting linguistic resources for.
Spoken dialog for e-learning supported by domain ontologies Dario Bianchi, Monica Mordonini and Agostino Poggi Dipartimento di Ingegneria dell’Informazione.
Multimodal Information Access Using Speech and Gestures Norbert Reithinger
Copyright 2002 Prentice-Hall, Inc. Chapter 2 Object-Oriented Analysis and Design Modern Systems Analysis and Design Third Edition Jeffrey A. Hoffer Joey.
Section 4.2 AQA Computing A2 © Nelson Thornes 2009 Types of Operating System Unit 3 Section 4.1.
Subtask 1.8 WWW Networked Knowledge Bases August 19, 2003 AcademicsAir force Arvind BansalScott Pollock Cheng Chang Lu (away)Hyatt Rick ParentMark (SAIC)
 Copyright 2008 Digital Enterprise Research Institute. All rights reserved. Semantic on the Social Semantic Desktop.
Chapter 3 DECISION SUPPORT SYSTEMS CONCEPTS, METHODOLOGIES, AND TECHNOLOGIES: AN OVERVIEW Study sub-sections: , 3.12(p )
An Ontological Framework for Web Service Processes By Claus Pahl and Ronan Barrett.
Page 1 Alliver™ Page 2 Scenario Users Contents Properties Contexts Tags Users Context Listener Set of contents Service Reasoner GPS Navigator.
Dept. of Computer Science University of Rochester Rochester, NY By: James F. Allen, Donna K. Byron, Myroslava Dzikovska George Ferguson, Lucian Galescu,
卓越發展延續計畫分項三 User-Centric Interactive Media ~ 主 持 人 : 傅立成 共同主持人 : 李琳山,歐陽明,洪一平, 陳祝嵩 水美溫泉會館研討會
TTCN-3 MOST Challenges Maria Teodorescu
A Common Ground for Virtual Humans: Using an Ontology in a Natural Language Oriented Virtual Human Architecture Arno Hartholt (ICT), Thomas Russ (ISI),
Agenda 1. What we have done on which tasks 2. Further specification of work on all our tasks 3. Planning for deliverable writing this autumn (due in December)
Group-oriented Modelling Tools with Heterogeneous Semantics Niels Pinkwart COLLIDE Research Group University of Duisburg, Germany.
A comprehensive framework for multimodal meaning representation Ashwani Kumar Laurent Romary Laboratoire Loria, Vandoeuvre Lès Nancy.
Introduction to Dialogue Systems. User Input System Output ?
Referring to Objects with Spoken and Haptic Modalities Frédéric LANDRAGIN Nadia BELLALEM & Laurent ROMARY LORIA Laboratory Nancy, FRANCE.
CSE573 Autumn /20/98 Planning/Language Administrative –PS3 due 2/23 –Midterms back today –Next topic: Natural Language Processing reading Chapter.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition, Turban, Aronson, and Liang 3-1 Chapter 3 Decision Support Systems:
Information state and dialogue management in the TRINDI Dialogue Move Engine Toolkit, Larsson and Traum 2000 D&QA Reading Group, Feb 20 th 2007 Genevieve.
1 Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents S. Kawamoto, et al. October 27, 2004.
PGNET, Liverpool JMU, June 2005 MediaHub: An Intelligent MultiMedia Distributed Platform Hub Glenn Campbell, Tom Lunney, Paul Mc Kevitt School of Computing.
Chapter 1 Basic Concepts of Operating Systems Introduction Software A program is a sequence of instructions that enables the computer to carry.
The “Spatial Turing Test” Stephan Winter, Yunhui Wu
SEESCOASEESCOA SEESCOA Meeting Activities of LUC 9 May 2003.
“Intelligent User Interfaces” by Hefley and Murray.
Software Architecture for Multimodal Interactive Systems : Voice-enabled Graphical Notebook.
Layers Architecture Pattern Source: Pattern-Oriented Software Architecture, Vol. 1, Buschmann, et al.
Application architectures Advisor : Dr. Moneer Al_Mekhlafi By : Ahmed AbdAllah Al_Homaidi.
SAP Integration with Oracle 11g Muhammad Raza Fatmi.
Cloud based linked data platform for Structural Engineering Experiment
Unit 2 User Interface Design.
External Services & Frameworks
Analysis models and design models
Multimodal Human-Computer Interaction New Interaction Techniques 22. 1
Map of Human Computer Interaction
Presentation transcript:

DFKI Approach to Dialogue Management Norbert Reithinger, Elsa Pecourt, Markus Löckelt

Dialog WS MITRE2 What we develop at DFKI Research goal: –Develop multimodal interactivity interfaces Hypotheses: –Multimodal interaction facilitates interaction –Analysis, dialog management and presentation are tightly connected Major task in our group: –Design and implement (parts of) the dialog backbone of such systems Design approach (our mantras) –Use general solutions for general problems –No processing and presentation without representation

Dialog WS MITRE3 Dialogue Management Complex interplay of Action Planner – the mind of the machine: –knows all other acting parties and how to handle them –Interaction Types: Request/Response, e.g., DB query, user interaction Active processes, e.g., route guidance Discourse Model(ler) – the memory of the machine Analysis/Presentation modules Functionalities Current emphasis: Flexible and adaptable to many functionalities Switch between applications during dialogs Reusable (comes with a price)

Dialog WS MITRE4 Multimodal Dialogue Backbone Public: Cinema, Phone, Fax, Mail, Biometrics Application Layer Mobile: Car and Pedestrian Navigation Tourist Information SmartKom-Mobile: Mobile Travel Companion Home: Consumer Electronics EPG System1: SmartKom SmartKom-Home: Infotainment Companion SmartKom-Public: Communication Companion

Dialog WS MITRE5 SmartKom 3 scenarios 14 applications 52 functionalities 3500 words at start 3 PCs (2xLinux, 1x Windows) (... and 12 partner institutions collaborating) (Source: Reithinger et al: SmartKom - Adaptive and Flexible Multimodal Access to Multiple Applications. In ICMI ’03)

Dialog WS MITRE6 Module Overview of SmartKom Expectations Common Ontology/ M3L Schema Modules related to discourse management

Dialog WS MITRE7 Top Level Ontology

Dialog WS MITRE8 Process Model

Dialog WS MITRE9 System 2: MIAMM – Speech and Haptics B2 B3 B1 B4 Application: Search in MP3 Database (DE, FR, EN) Haptic buttons enable new interaction Simulated with Phantom devices Other visualisation metaphors

Dialog WS MITRE10 Modules of MIAMM Domain-Model Music Database Speech Recognition Speech Analysis Speech-Prompts MP3-Player Visual / haptic / tactile Interaction Dialog Manager Multimodal- Fusion Dialog- Memory Action- Planner Common Rep. (MMIL)

Dialog WS MITRE11 Adaptation Needed Representation/Ontology: –Used by almost all modules Provided by partners (SmartKom and MIAMM) –Basis of reasoning in the Discourse Modeller (SmartKom) Interpretation rules in Speech Interpretation (SPIN) to create semantic representations Plan operators in the Action Planner Interface to the backend application/application logic –E.g., we cannot work very well with the pronpts/text in the backend Functionality that could be skipped: –Presentation plans for the Presentation Planner –Generator rules for the Text Generator Adaptation time per application in SmartKom: approx. 1-2 person months (2-3 weeks, 2-3 persons) Adaptation time per application in SmartKom: approx. 1-2 person months (2-3 weeks)

Dialog WS MITRE12 Approach in the Action Planner: Communication Channels Unified treatment of all communication channels (user modalities, internal and external functionalities) Input and output channels defined for every module communicating with AP. –In MIAMM: MMF, VisHapTac, MiaDoMo, MP3 Player –In SmartKom: Intention Recognition, Discourse Modeller, Dynamic Help, Presentation Planning, Function Modelling Processing Approach: Communicative Games

Dialog WS MITRE13 Communicative Games (1) Communicative Games (CGs) for the modelling of dialogues (plan operators) –A CG consists of a sequence of communication acts (dialogue moves) e.g. request, response, inform, greeting –Can be embedded in other CG –synchronous and asynchronous communication possible The Action Planner –Creates a plan made of CGs, to achieve the goals of the user, –triggers and controls the execution of the actions

Dialog WS MITRE14 Communicative Games (MIAMM) Interaction QueryPresentation User „I want something from the 90‘s“ „Here are the results“ requestresponse

Dialog WS MITRE15 Communicative Games Interaction QueryPresentation User MiaDoMo (Database) ReplyQuery query results Extern requestresponse

Dialog WS MITRE16 Communicative Games Interaction QueryPresentation User Database ReplyQuery External Clarification dialogue QuestionAnswer requestresponse „What kind of music are you looking for” (System initiative)

Dialog WS MITRE17 Plan operators in MIAMM I want something from the 90´s Here are the results

Dialog WS MITRE18 Plan operators in MIAMM (2) query results

Dialog WS MITRE19 Successor States Planing Approach: Backward Chaining provides(Y) needs(D) condition(D=x) Goal provides() needs(X,Y) provides(X) needs(A,B) provides(C) needs() provides(B) needs(D) provides(A) needs(C) provides(F,G) needs(H) provides(D) needs(E) Current State provides(?) needs(?)

Dialog WS MITRE20 Pros and Cons of Our Approach Pros: Generic Methods for –Analysis/Generation –Reference processing –Action Planning Integration of multimodal I/O Neutral to functionalities Straightforward method of adaptation Cons: Needs deep(-er) modeling of the domain Lots of modules need to go along for a new application Difficult to integrate functionalities like the WS- backend which contains e.g. answer texts Separation of Dialog History and Action Planner

Dialog WS MITRE21 What Would We Like to Cover Error handling in the planner: –MIAMM: straightforward solution as plan operators –SmartKom: separate Dynamic Help module (due to reasons of project structure) Less applications, more generic dialog phenomena –More explicit feedback about the systems intentions and the ongoing dialog to the user –Dialog processing better adapted to the user –Knowledge about argumentations/discussions/ negotiations (current bias on access to functionalities) Questions: –Which abstractions are really needed? –Which abstractions are useful?

Dialog WS MITRE22 Thank you very much for your attention! Multimodal projects with participation of DFKI –SmartKom (BMBF): –MIAMM (EU): Multidimensional Information Access using Multiple Modalities: –COMIC (EU): COnversational Multimodal Interaction with Computers: –VirtualHuman (BMBF): Virtual agents for education