Research about dialogue and dialogue systems and the department of linguistics goal: –develop theories about human dialogue which can be used when building.

Slides:



Advertisements
Similar presentations
INTERACTIVE VOICE RESPONSE SYSTEM (IVRS)
Advertisements

Human Computer Interface
An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
ENHANCED PABX SYSTEM WITH REROUTING/LOGGING SYSTEM
1 Microsoft Access 2002 Tutorial 9 – Automating Tasks With Macros.
MEPO Training MEPO Database Access Training Presentation Copyright 2011 Rodger B. Fluke, MPA.
Stat-JR: eBooks Richard Parker. Quick overview To recap… Stat-JR uses templates to perform specific functions on datasets, e.g.: – 1LevelMod fits 1-level.
XP Tutorial 9 New Perspectives on Microsoft Windows XP 1 Microsoft Windows XP Exploring Your Network Tutorial 9.
COMP 3715 Spring 05. Computer Interface Interaction between human and computer Has to deal with two things  User’s mental model Different user has different.
Siridus Specification, Interaction and Reconfiguration in Dialogue Understanding Systems an information state approach to flexible spoken dialogue systems.
Dialogue Systems 2 GSLT Spring Purpose The purpose of the course is to –do real research on dialogue systems by –building on existing systems developed.
Human Centric Computing Assignment 2 Proposal 15.
Automating Tasks With Macros
LE TRINDIKIT A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Spoken Dialogue Technology How can Jerry Springer contribute to Computer Science Research Projects?
Goteborg University Dialogue Systems Lab WP1: GoDiS VCR application Edinburgh TALK meeting 7/
Question Accommodation and Information States in Dialogue
Automating Tasks With Macros. 2 Design a switchboard and dialog box for a graphical user interface Database developers interact directly with Access.
Information, action and negotiation in dialogue systems Staffan Larsson Kings College, Jan 2001.
TrindiKit A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach.
Menu2dialog Staffan Larsson, Robin Cooper, Stina Ericsson Department of linguistics Göteborgs Universitet.
LE A toolkit for building and experimenting with dialogue move engines and systems, based on the information state approach TrindiKit.
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.
Course: Introduction to Computers
Systems Analysis and Design in a Changing World, 6th Edition
Web Self Service Take Home Message Web Self Service gives CRM information access to assigned non-CRM users.
Use Cases Yonglei Tao.
Module Designing Computer-based Information Systems
Introduction To Computer System
Improving Speech Applications with Video August 9 th 2006 David Multimedia Research Department Avaya Labs Research.
Creating a Web Site to Gather Data and Conduct Research.
©RavichandranUser interface Slide 1 User interface design.
Copyright © 2007, Oracle. All rights reserved. Managing Concurrent Requests.
Multimodal Information Access Using Speech and Gestures Norbert Reithinger
The Information State approach to dialogue modelling Staffan Larsson Dundee, Jan 2001.
In the next step you will enter some data records into the table. This can be done easily using the ‘Data Browser’. The data browser can be accessed via.
An information state approach to natural interactive dialogue Staffan Larsson, Robin Cooper Department of linguistics Göteborg University, Sweden.
1 Rev 2: 3/4/2014 LWAF Plant Database - AKA “Accession Database” - Please note that this presentation has note pages using PowerPoint notes capabilities.
Week 2 Lab1 User Interface Design Dina A. Said
1 Course Title: Visual Basic Programming Topic: Introduction to programming Languages (Visual basic 6.0) Lecturer: Mahamud Ahmed Jimale, BsIT, MsCs, CCNA,
Spoken Dialog Systems and Voice XML Lecturer: Prof. Esther Levin.
UNESCO ICTLIP Module 4. Lesson 2 Database Design, and Information Storage and Retrieval Lesson 2. Database creation using WinISIS.
Design Options for Multimodal Web Applications Adrian Stanciulescu and Jean Vanderdonckt {stanciulescu, UCL/IAG/BCHI.
HARDWARE INPUT DEVICES GETTING DATA INTO THE COMPUTER.
DenK and iCat Two Projects on Cooperative Electronic Assistants (CEA’s) Robbert-Jan Beun, Rogier van Eijk & Huub Prüst Department of Information and Computing.
Introduction to Computational Linguistics
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.
XP New Perspectives on Microsoft Office Access 2003 Tutorial 10 1 Microsoft Office Access 2003 Tutorial 10 – Automating Tasks With Macros.
Introduction to KE EMu
Introduction to KE EMu Unit objectives: Introduction to Windows Use the keyboard and mouse Use the desktop Open, move and resize a.
Introduction to KE EMu Unit objectives: Introduction to Windows Use the keyboard and mouse Use the desktop Open, move and resize a.
Create Windows Setup and Deployment Projects Windows Development Fundamentals LESSON 5.2.
Software Interfaces. Learning Objectives Describe the characteristics of different types of user interfaces. Discuss the types of user interfaces which.
COMPUTER PROGRAMMING I 3.01 Apply Controls Associated With Visual Studio Form.
Decision Support System by Simulation Model (Ajarn Chat Chuchuen) 1 Chapter 6 User Interface Management.
 Learn the mechanics of using App Inventor to build apps.  Learn how to design an app’s user interface with the App Inventor Designer, and its behavior.
Databases – Part 1 Databases– Part 1 Lesson 3 & 4.
SchoolSuccess for Coordinators
Development Environment
System.
Moveware Client Wiki.
Human Computer Interaction Lecture 21,22 User Support
Manage Call Handling Profiles
Microsoft Excel 2003 Illustrated Complete
How to register and use ODMAP for Fire/EMS and other partners
STUDENT INFORMATION SYSTEM (SIS)
Managing Dialogue Julia Hirschberg CS /28/2018.
Contents Introduction Motivation Objectives
Presentation transcript:

research about dialogue and dialogue systems and the department of linguistics goal: –develop theories about human dialogue which can be used when building dialogue systems –explore the use of dialogue systems as interfaces to applications and services Some projects –TRINDI: Task-Oriented and Instructional Dialogue –SIRIDUS: Specification, Interaction and Reconfiguration in Dialogue Understanding Systems –D´Homme: Dialogues in the Home Environment

From menu to dialogue Staffan Larsson Institutionen för lingvistik Göteborgs Universitet

Background Many applications and services have menu-based interfaces –mobile phone –video –computer –automatic cinema ticket booking via phone But menus have certain disadvantages Dialogue systems provide more user- friendly interfaces

Overview GoDiS: a dialogue system Meny vs. dialogue Menu components Dialogue plans Converting menus to dialogue plans Examples

GoDiS: a dialogue system dialogue manager –implemented using the information state approach –based on a theory about dialogue based on ”Questions Under Discussion” and dialogue plans –allows flexible dialogue

GoDiS architecture modules: –speech recogniser –language interpreter –dialogue manager –language generator –speech synthesis Information state resources –lexicon, database, domain knowledge

input inter- pret Information State lexicon control updateselect gene- rate output data- base domain

Typical human-computer dialog in a travel agency S: Hello, how can I help you? U: I want price information please S: Where do you want to go? U: Paris S: How do you want to travel? U: A flight please S: When do you want to travel U: April S: what class did you have in mind? … S: The price is $123

Typical human-human dialogue S(alesman), C(ustomer) S: hi C: flights to Paris S: when do you want to travel? C: April, as cheap as possible...

Flexible dialogue with GoDiS in the travel agency domain answering question which have not yet been asked, but which are relevant to some task –S: when do you want to travel? –U: in April, as cheap as possible providing information without specified task –S: hello –U: flights to Paris

Menus vs. dialogue: Drawbacks of menus User must follow predesigned menu structure this structure may be complicated and difficult to learn menus allow only one activity at a time

Menu vs. dialogue: Advantages of flexible dialogue provide information in any order provide information without pre- specifying the task doing several things at once not necessary to learn menu structure

Menu components multiple-choice list –the user selects one of several prespecified choices dialogue window –user types requested information tickbox –user ticks box (or not) system message –information from system; user clicks ”OK”

Sample menu from a Noka 3210 search phonebook –dialogue window to type in name Name: _______ –message showing the number Kalle –tickbox: whether to call this person Call –if a call is made, a message: Calling

Dialogue plans dialogue plans are partial specifications of how the system should act in a dialogue –action sequences, conditions etc Actions: –find the answer to a question –answer a question –inform –search database –domain-specific actions, e.g. phone up number

Questions yes/no-question –” Do you want to call NN?” wh-question: who, what, which.... –”Who do you want to search for?” alternative-question –”Do you want to search, add to, erase from or change the phonebook?”

Converting from menu to dialogue plan MenuPlan multi-choice listalternative question tickboxyes/no-question dialogue windowwh-question messageinform

the menu again search phonebook –dialogue window to type in name –message showing the number –tickbox: whether to call this person –if a call is made, a message

corresponding plan 1 question: what name? 2 search database for NUMBER matching the name 3 answer: the number is (NUMBER) 4 ask: do you want to call? 5 if yes then call up number:NUMBER inform: calling NAMN

another plan: assign ringing tone 1 ask: what name? 2 ask: which ringing tone? 3 assign the ringing tone to the name 4 inform: the ringing tone for (NAME) is no (RINGING TONE)

Example 1: standard menu navigation U:Go to the phonebook S: Phonebook. Do you want to search, add, or remove an entry, or assign a ringing tone? U: Assign ringing tone S: What name? U: John S: Which ringin tone? U: Bossanova S: The ringing tone for John is now Bossanova.

Example 2: providing information which has not been asked for U: Assign ringing tone S: What name? U: Bossanova for John S: The ringing tone for John is now Bossanova.

Example 3: provide information without assigning task(I) U: Bossanova for John S: The ringing tone for John is now Bossanova.

Example 4: provide information without assigning task (II) U: 5 o’clock S: Do you want to set the clock or the alarm clock? U: alarm clock S: the alarm clock is now set to 5

Example 5 (video): system requests missing information U: record from 19:30 to 20:00 today S: What channel? U: Seven S: OK, I will record channel 7 from 19:30 to 20:00 today.

Demo GoDiS has been adapted to several domains, including –travel agency –mobile phone interface (course project) –interface to intellegent house –cinema ticket booking (MA thesis) –internet search (MA thesis) –telephone receptionist We will give a demo of the mobile phone interface

demo GoDiS i resebyrådomänen F317

Dialogplaner handling: A handlingssekvens: A 1,A 2,..., A n villkorssatser: –if_then(P,C) P är ett villkor Om P är uppfyllt, gör C