- Up -
Next >>
Table of Contents
Table of Contents
1 Examples of Dialogue Systems
1.1 Dialogue Processing
1.1.1 Warming Up
1.1.2 General Dialogue characteristics
1.2 Speaking Elevator: Examples of Required Behaviour
1.2.1 Introduction of the Speaking Elevator Sytem
1.2.2 Turn-taking
1.2.3 Adjacency pairs and insertions
1.2.4 Grounding
1.2.5 Dialogue context
1.2.6 Ellipsis
1.2.7 Reference resolution
1.3 TRAINS Dialogue System Description
1.3.1 The TRAINS user interface.
1.3.2 The domain
1.3.3 A TRAINS example dialogue
1.3.4 The mode of interaction
1.3.5 Planning
1.3.6 How the user input is interpreted
1.3.7 Dealing with the input
1.4 TRAINS General Dialogue Characteristics
1.4.1 Turn-taking
1.4.2 Adjacency pairs and insertions
1.4.3 Grounding
1.4.4 Dialogue context
1.4.5 Ellipsis
1.4.6 Reference resolution
1.4.7 Mixed initiative
1.5 TRAINS References
2 Finite States Techniques for Dialogue Processing
2.1 FSA-based Dialogue Systems
2.1.1 Processing dialogue with finite state systems
2.1.2 A simple FSA example
2.2 Extending FSA
2.2.1 Why Extending FSA?
2.2.2 Grounding Extension 1
2.2.3 Grounding Extension 2
2.2.4 Grounding Extension 3
2.2.5 And what about Repair?
2.3 An In-depth Look at the Speaking Elevator
2.3.1 The Saarbrücken CL department's Speaking Elevator
2.3.2 How does the dialogue progress?
2.3.3 An additional memory
2.3.4 How long does the system wait for a response?
2.3.5 How does the elevator deal with unrecognised utterances or inconsistent input?
2.3.6 And what happens if the elevator does understand the input?
2.3.7 How is the user input confirmed?
2.3.8 During the trip...
2.3.9 What happens when there is ambiguous input?
2.3.10 Speaking elevator reference
2.4 Dialogue Characteristic and Extension of the Elevator
2.4.1 Turn-taking
2.4.2 Adjacency pairs and insertions
2.4.3 Grounding
2.4.4 Dialogue context
2.4.5 Ellipsis
2.4.6 Reference resolution
2.4.7 Mixed initiative
2.5 Summary and Outlook
2.5.1 Advantages and disadvantages
2.5.2 The CSLU tool
2.5.3 Beyond Finite State Techniques
3 Speech Acts and Dialogue Management
3.1 Introduction to Speech Acts
3.1.1 The background
3.1.2 What are speech acts and what do they do?
3.1.3 Searle's Classification of Speech Acts
3.2 Speech Acts in Dialogue Management
3.2.1 Important Aspects
3.2.2 Context and Dialogue Management
3.2.3 More Context
3.3 Example Dialogue Annotation Schemes
3.3.1 Introduction of Dialogue Acts
3.3.2 HCRC Map task
3.3.3 HCRC Map task: Levels of annotation
3.3.4 Verbmobil 2
3.3.5 Verbmobil 2: Levels of annotation
3.3.6 TRAINS
3.3.7 TRAINS: The approach
3.3.8 DAMSL
3.3.9 DAMSL: The scheme
3.3.10 Automated tagging of dialogue acts
3.4 TRIPS
3.4.1 System Architecture
3.4.2 Human-computer communication
3.4.3 The Interpretation Manager
3.4.4 The Speech recogniser
3.4.5 The Chart parser
3.4.6 Task Manager
3.4.7 The Reference and Discourse Context Components
3.4.8 The Generation Manager
3.4.9 Speech acts in TRIPS
3.5 References
3.6 Practical exercise.
3.6.1 A small dialogue act taxonomy
3.6.2 Instructions
3.7 Comments on the Exercise
3.7.1 Annotation reliability
3.7.2 Multi-functional utterances
3.7.3 Sub-dialogues
3.7.4 An example annotation
4 Practical Session (MiLCA-Summer-School Tübingen, 2003)
4.1 Exercise: Philips train information system
4.2 The CLT tool
4.2.1 Dialogue Specifications
4.2.2 Devices and Variables
4.2.3 The dialogue automaton
4.2.4 Nodes
Output nodes
Input nodes
Variable nodes
Condition nodes
Subgraph and Procedure nodes
4.3 Running a dialogue
4.4 Exercise: Dialogue design using the CLT tool
4.5 Designing a speaking elevator dialogue
Bibliography
Index
- Up -
Next >>
Dimitra Tsovaltzi
,
Stephan Walter
and
Aljoscha Burchardt
Version 1.2.5 (20030212)