LE4-8314 1 A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach TrindiKit.

Slides:



Advertisements
Similar presentations
An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
Advertisements

Negotiative dialogue some definitions and ideas. Negotiation vs. acceptance Clark’s ladder: –1. A attends to B’s utterance –2. A percieves B’s utterance.
Key-word Driven Automation Framework Shiva Kumar Soumya Dalvi May 25, 2007.
Empirical and Data-Driven Models of Multimodality Advanced Methods for Multimodal Communication Computational Models of Multimodality Adequate.
Siridus Specification, Interaction and Reconfiguration in Dialogue Understanding Systems an information state approach to flexible spoken dialogue systems.
Issues Under Negotiation Staffan Larsson Dept. of linguistics, Göteborg University SigDial, 15/
LE TRINDIKIT A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Goteborg University Dialogue Systems Lab Introduction to TrindiKit Dialogue Systems 2004 Staffan Larsson.
Supervised by Prof. LYU, Rung Tsong Michael Department of Computer Science & Engineering The Chinese University of Hong Kong Prepared by: Chan Pik Wah,
The Data Mining Visual Environment Motivation Major problems with existing DM systems They are based on non-extensible frameworks. They provide a non-uniform.
Goteborg University Dialogue Systems Lab WP1: GoDiS VCR application Edinburgh TALK meeting 7/
Question Accommodation and Information States in Dialogue
Research about dialogue and dialogue systems and the department of linguistics goal: –develop theories about human dialogue which can be used when building.
School of Computing and Mathematics, University of Huddersfield Knowledge Engineering: Issues for the Planning Community Lee McCluskey Department of Computing.
GoDiS (Gothenburg Dialogue System) with application to instructional text and dialogue ESSLLI, Helsinki 21st Aug 2001 Staffan Larsson
TrindiKit A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Issues Under Negotiation Staffan Larsson Dept. of linguistics, Göteborg University NoDaLiDa, May 2001.
Menu2dialog Staffan Larsson, Robin Cooper, Stina Ericsson Department of linguistics Göteborgs Universitet.
PROMPT: Algorithm and Tool for Automated Ontology Merging and Alignment Natalya F. Noy and Mark A. Musen.
Introduction to the TrindiKit Dialogue Systems 2 GSLT spring 2003 Staffan Larsson
Introduction to the TrindiKit ESSLLI, Helsinki 20th Aug 2001 Staffan Larsson
Rough schedule Multimodal, multi-party dialogue [30 min] D’Homme, SIRIDUS [10 min] –dialogues with networked devices in a smart house SRI demo (DM), (IBL.
Goteborg University Dialogue Systems Lab GoDiS and TrindiKit MITRE workshop 27/10-03 Staffan Larsson Göteborg University Sweden.
WP1 UGOT demos 2nd year review Saarbrucken Mar 2006.
CSC230 Software Design (Engineering)
Copyright Arshi Khan1 System Programming Instructor Arshi Khan.
Application architectures
CS-EE 481 Spring Founders Day, 2005 University of Portland School of Engineering Project Pocket Gopher Conversational Learning Agent Team Josh Jones.
Java Beans.
Some Thoughts on HPC in Natural Language Engineering Steven Bird University of Melbourne & University of Pennsylvania.
Software Development Stephenson College. Classic Life Cycle.
Multimodal Information Access Using Speech and Gestures Norbert Reithinger
Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001.
The Information State approach to dialogue modelling Staffan Larsson Dundee, Jan 2001.
TrindiKit Staffan Larsson Göteborg University Sweden.
TrindiKit: A Toolkit for Flexible Dialogue Systems Staffan Larsson Kyoto, Japan 2003.
An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
R R R 1 Frameworks III Practical Issues. R R R 2 How to use Application Frameworks Application developed with Framework has 3 parts: –framework –concrete.
From information exchange to negotiation Staffan Larsson Göteborg University
FlexElink Winter presentation 26 February 2002 Flexible linking (and formatting) management software Hector Sanchez Universitat Jaume I Ing. Informatica.
TrindiKit. TrindiKit architecture & concepts what’s in TrindiKit? comparison with other architectures this talk.
| | Cortana announcing new hosts/services | | w00ps… is that your password? Cortana found it.
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)
October 2005CSA3180 NLP1 CSA3180 Natural Language Processing Introduction and Course Overview.
Evaluation of Agent Building Tools and Implementation of a Prototype for Information Gathering Leif M. Koch University of Waterloo August 2001.
©2003 Paula Matuszek Taken primarily from a presentation by Lin Lin. CSC 9010: Text Mining Applications.
The Information State approach to dialogue modelling + TrindiKit AI-course, Chalmers April 2002 Staffan Larsson.
DIALOG SYSTEMS FOR AUTOMOTIVE ENVIRONMENTS Presenter: Joseph Picone Inst. for Signal and Info. Processing Dept. Electrical and Computer Eng. Mississippi.
© 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.
GoDiS AI-course, Chalmers April 22, 2002 Staffan Larsson.
Information-State Dialogue Modelling in Several Versions HS Dialogmanagement, SS 2002 Universität Saarbrücken Michael Götze.
Abstract A Structured Approach for Modular Design: A Plug and Play Middleware for Sensory Modules, Actuation Platforms, Task Descriptions and Implementations.
Dialog Models September 18, 2003 Thomas Harris.
1 Service Creation, Advertisement and Discovery Including caCORE SDK and ISO21090 William Stephens Operations Manager caGrid Knowledge Center February.
1 These courseware materials are to be used in conjunction with Software Engineering: A Practitioner’s Approach, 5/e and are provided with permission by.
TrindiKit: A Toolkit for Flexible Dialogue Systems AI course, spring 2003 Staffan Larsson.
Slide 1 Ch 13 Application architectures Generic architectures that can be configured and adapted to create a system that meets specific requirements Can.
Lecture 21: Component-Based Software Engineering
Of An Expert System.  Introduction  What is AI?  Intelligent in Human & Machine? What is Expert System? How are Expert System used? Elements of ES.
Abdul Rahim Ahmad MITM 613 Intelligent System Chapter 10: Tools.
Speech Processing 1 Introduction Waldemar Skoberla phone: fax: WWW:
Flowcharts C++ Lab. Algorithm An informal definition of an algorithm is: a step-by-step method for solving a problem or doing a task. Input data A step-by-step.
Architectural Mismatch: Why reuse is so hard? Garlan, Allen, Ockerbloom; 1994.
©Ian Sommerville 2007COTS-based System Engineering Slide 1 COTS-based System Engineering.
Application architectures Advisor : Dr. Moneer Al_Mekhlafi By : Ahmed AbdAllah Al_Homaidi.
Architecture Components
An Integrated Theory of the Mind
Where We’re Going Problem Definition Value Proposition Tasks
Presentation transcript:

LE A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach TrindiKit

LE TrindiKit dialogue theory (IS, rules, moves etc,) domain knowledge, NL modules,... domain independent DME domain-specific system Building a system

LE Architecture based on information states Modules (dialogue move engine, input, interpretation, generation, output etc.) access the information state) Resources (databases, lexicons, domain knowledge etc.) are hooked up to the information state TrindiKit architecture

LE Explicit information state datastructure makes systems more transparent Update rules provide an intuitive way of formalising theories in a way which can be used by a system TrindiKit’s modularity provides simple and efficient methods for reconfiguration Modularity also encourages reusability TrindiKit enables rapid prototyping of simple systems, as well as advanced research systems ****** TrindiKit Features

LE Build or select from existing components: Type of information state (DRS, record, set of propositions, frame,...) A set of dialogue moves Information state update rules, including rules for integrating and selecting moves DME Module algorithm(s) and basic control algorithm ****** Building a DME

LE Domain-specific system Build or select from existing components: Resources, e.g. –databases for domain –grammars, lexicons –domain knowledge, e.g. plan libraries etc. Modules, e.g. –input –interpretation –generation –output

LE A library of datatype definitions (records, DRSs, sets, stacks etc.) A language for writing information state update rules Methods and tools for visualising the information state debugging facilities TrindiKit components

LE A language for defining update algorithms used by TrindiKit modules to coordinate update rule application A language for defining basic control structure, to coordinate modules A library of basic ready-made modules for input/output, interpretation, generation etc.; A library of ready-made resource interfaces, e.g. to hook up databases, domain knowledge etc. TrindiKit components (cont’d)

LE Planned for 2.0 Generic WWW interface Allowing both serial and asynchronous systems GUI for increased usability and overview, including tools for building systems Modules for speech input and output, for using off-the-shelf products Improved facilities for handling dialogue plans Extend libraries of ready-made modules and resources *** ***

LE GoDiS and IMDiS – information state based on Questions Under Discussion MIDAS – DRS information state, first-order reasoning EDIS – information state based on PTT Autoroute – information state based on Conversational Game Theory Systems

LE An experimental dialogue system built using the TrindiKit GoDiS

LE Information-seeking dialogue Information state based Ginzburg’s notion of Questions Under Discussion (QUD) Dialogue plans to drive dialogue Simpler than general reasoning and planning More versatile than frame-filling and finite automata GoDiS features

LE PRIVATE =PLAN = AGENDA = { findout(?return) } SHARED = findout(? x.month(x)) findout(? x.class(x)) respond(? x.price(x)) COM = dest(paris) transport(plane) task(get_price_info) QUD = LM = { ask(sys, x.origin(x)) } BEL = { } TMP = (same structure as SHARED) Sample GoDiS information state

LE integrateAnswer Before an answer can be integrated by the system, it must be matched to a question on QUD pre: eff: in( SHARED.LM, answer(usr, A)) fst( SHARED.QUD, Q) relevant_answer(Q, A) pop( SHARED.QUD ) reduce(Q, A, P) add( SHARED.COM, P) Sample update rule

LE Adapted for travel agency and autoroute domains Further domain adaptations in progress: –cinema booking –handheld computer –mobile phone Lexicons for English and Swedish Question and task accommodation to enable mixed initiative Simple “optimistic” grounding strategy Focus intonation based on information state contents GoDiS features (cont’d)