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

Slides:



Advertisements
Similar presentations
Visual Scripting of XML
Advertisements

An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
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.
Goteborg University Dialogue Systems Lab Using TrindiKit and GoDiS as OAA resources TALK Edinburgh 7/
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/
Goteborg University Dialogue Systems Lab Introduction to TrindiKit Dialogue Systems 2004 Staffan Larsson.
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.
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.
Introduction to the TrindiKit Dialogue Systems 2 GSLT spring 2003 Staffan Larsson
LE A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach TrindiKit.
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.
Guided Conversational Agents and Knowledge Trees for Natural Language Interfaces to Relational Databases Mr. Majdi Owda, Dr. Zuhair Bandar, Dr. Keeley.
CSC230 Software Design (Engineering)
Windows.Net Programming Series Preview. Course Schedule CourseDate Microsoft.Net Fundamentals 01/13/2014 Microsoft Windows/Web Fundamentals 01/20/2014.
CS-EE 481 Spring Founders Day, 2005 University of Portland School of Engineering Project Pocket Gopher Conversational Learning Agent Team Josh Jones.
Introduction to Computer and Programming CS-101 Lecture 6 By : Lecturer : Omer Salih Dawood Department of Computer Science College of Arts and Science.
Some Thoughts on HPC in Natural Language Engineering Steven Bird University of Melbourne & University of Pennsylvania.
COMPUTER PROGRAMMING Source: Computing Concepts (the I-series) by Haag, Cummings, and Rhea, McGraw-Hill/Irwin, 2002.
Software Development Stephenson College. Classic Life Cycle.
Views The architecture was specifically changed to accommodate multiple views. The used of the QStackedWidget makes it easy to switch between the different.
©Ian Sommerville 2000 Software Engineering, 6th edition. Chapter 10Slide 1 Architectural Design l Establishing the overall structure of a software system.
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.
 CS 5380 Software Engineering Chapter 2 – Software Processes Chapter 2 Software Processes1.
TrindiKit Staffan Larsson Göteborg University Sweden.
Federal XML Naming and Design Rules and Guidelines Mark Crawford.
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.
WSMX Execution Semantics Executable Software Specification Eyal Oren DERI
From information exchange to negotiation Staffan Larsson Göteborg University
Architectural Design lecture 10. Topics covered Architectural design decisions System organisation Control styles Reference architectures.
FlexElink Winter presentation 26 February 2002 Flexible linking (and formatting) management software Hector Sanchez Universitat Jaume I Ing. Informatica.
©Ian Sommerville 2000 Software Engineering, 6th edition. Chapter 10Slide 1 Architectural Design l Establishing the overall structure of a software system.
Architectural Design Yonsei University 2 nd Semester, 2014 Sanghyun Park.
TrindiKit. TrindiKit architecture & concepts what’s in TrindiKit? comparison with other architectures this talk.
Overview of MOT Knowledge representation system : Basic Modeling Editor LexiconGrammarSemantics Pragmatics MOT Editor.
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.
© 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.
CSC480 Software Engineering Lecture 10 September 25, 2002.
GoDiS AI-course, Chalmers April 22, 2002 Staffan Larsson.
Information-State Dialogue Modelling in Several Versions HS Dialogmanagement, SS 2002 Universität Saarbrücken Michael Götze.
Dialog Models September 18, 2003 Thomas Harris.
Digital Libraries1 David Rashty. Digital Libraries2 “A library is an arsenal of liberty” Anonymous.
1 Service Creation, Advertisement and Discovery Including caCORE SDK and ISO21090 William Stephens Operations Manager caGrid Knowledge Center February.
1 Software Engineering: A Practitioner’s Approach, 6/e Chapter 15a: Product Metrics for Software Software Engineering: A Practitioner’s Approach, 6/e Chapter.
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.
CS562 Advanced Java and Internet Application Introduction to the Computer Warehouse Web Application. Java Server Pages (JSP) Technology. By Team Alpha.
TrindiKit: A Toolkit for Flexible Dialogue Systems AI course, spring 2003 Staffan Larsson.
Of An Expert System.  Introduction  What is AI?  Intelligent in Human & Machine? What is Expert System? How are Expert System used? Elements of ES.
Speech Processing 1 Introduction Waldemar Skoberla phone: fax: WWW:
THE EYESWEB PLATFORM - GDE The EyesWeb XMI multimodal platform GDE 5 March 2015.
Slide 1 Chapter 8 Architectural Design. Slide 2 Topics covered l System structuring l Control models l Modular decomposition l Domain-specific architectures.
Application architectures Advisor : Dr. Moneer Al_Mekhlafi By : Ahmed AbdAllah Al_Homaidi.
CIS 375 Bruce R. Maxim UM-Dearborn
An Integrated Theory of the Mind
Where We’re Going Problem Definition Value Proposition Tasks
Presentation transcript:

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

LE TRINDIKIT 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

LE Features TRINDIKIT enables rapid prototyping of simple systems, as well as advanced research systems TRINDIKIT’s modularity provides simple and efficient methods for reconfigurationModularity also encourages reusability 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

LE TRINDIKIT architecture

LE A library of datatype definitions (records, DRSs, sets, stacks etc.) in terms of conditions and operations which provide the basic building blocks for formulating information state update rules Methods for accessing the information state, implemented as a syntax for update rules Methods and tools for visualising the information state debugging facilities Generic WWW interface* * planned for TRINDIKIT 2.0 TRINDIKIT components

LE TRINDIKIT components (cont’d) A language for defining update algorithms used by TRINDIKIT modules to coordinate update rule application A language for defining basic control structure, allowing both serial and asynchronous* systems A library of basic ready-made modules for input/output (incl. speech), interpretation, generation, handling dialogue plans etc.; GUI* for increased usability and overview, including tools for building systems Resource interfaces, e.g. to hook up grammars, SQL databases, WWW agents etc.

LE Building a system 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), including control algorithm Resources: databases, grammars, plan libraries etc., or external modules (optionally) additional modules, datatypes

LE Building a system (cont’d) TRINDIKIT dialogue theory (IS, rules, moves etc,) domain knowledge (resources) generic system domain-specific system

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

LE An experimental dialogue system built using the TRINDIKIT GoDiS

LE GoDiS architecture

LE Information state based Ginzburg’s notion of Questions Under Discussion (QUD) Dialogue plans to drive dialogue Information-seeking dialogue QUD and dialogue plans provide the right level of complexity for information-seeking dialogue; simpler then general reasoning and planning, but more versatile then 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 = (*mirrors 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 (also being adapted to cinema booking, and to function as dialogue interface to a handheld computer and a mobile phone) Lexicons for english and swedish; lexicon can be switched dynamically Question and task accommodation to enable mixed initative; influenced by Lewis’ (1979) Focus intonation based on information state contents GoDiS features (cont’d)

LE GoDiS has been hooked up to IBM’s ViaVoice, an off-the-shelf speech synthesiser Default intonation gives incoherent impression, mainly because of presuppositions failures Chu & Nakatani (2000) put focus on features; this is insufficient in e.g. the travel agency domain Focus and intonation

LE GoDiS can control focus intonation based on the contents of the information state Currently implemented: a simple version of Pulman’s theory of parallellism; focus depends on what has been established in the dialogue In the near future: also use QUD to control focus intonation Focus and intonation (cont’d)