Dialog system
From Wikipedia, the free encyclopedia
A Dialog system is a computer system intended to converse with a human. Dialog systems have employed text, speech, graphics, haptics, gestures, face configurations, body positions, emotions, and other modes for communicative intent on both the input and output channel. Architectures for dialog systems vary, but an architecture for a typical spoken dialog system is shown in the figure below.
What does and does not constitute a dialog system may be debatable. The typical GUI wizard does engage in some sort of dialog, but it includes very few of the common dialog system components, and dialog state is trivial.
Contents |
[edit] Components
There are many different architectures for dialog systems. What sets of components are included in a dialog system, and how those components divide up responsibilities differs from system to system. Principal to any dialog system is the dialog manager, which is a component or set of components that manages the state of the dialog.
- dialog manager
- interaction manager
- input recognizer/decoder
- parser
- confidence annotator
- multi-modal fusion
- output generator
- natural language generator
- gesture generator
- layout engine
- output renderer
- text-to-speech engine
- talking head
- robot or avatar
In addition to the components above, which are part of the dialog system proper, there are often other components involved. These other components are common to many computer systems.
- real (or virtual) world event detection
- operating system
- messaging layer
- database
- logging
- i/o devices
- [[high-level control system
- machine learning facilities
[edit] Types of Systems
Dialog systems fall into many categories, the following is a list of such categories along a few dimensions. Many of the following categories overlap and the distinctions may not be well established.
- by device
- telephone-based systems
- PDA systems
- in-car systems
- robot systems
- desktop/laptop systems
- native
- in-browser systems
- in-virtual machine
- in-virtual environment
- robots
- by UI/modality
- text-based
- spoken language
- graphical user interface
- multi-modal
- by style/initiative
- command-based
- menu-driven
- natural language
- speech graffiti
- computer-initiative
- user-initiative
- mixed-initiative
- task-based
- plan-based
- collaborative
- turn-based
- event-based
- by application
- information service
- command-and-control
- entertainment
- education/tutorial
- edutainment
- reminder systems
- companion systems
- healthcare
- eldercare
- assistive/access systems
[edit] Implementations
[edit] Toolkits and Architectures
- Galaxy
- DIPPER: dialogue prototyping equipment and resources
- Olympus
- Ariadne
- The Universal Speech Interface
- Midiki
- TRINDIKIT
- VXML
- BeVocal Café
- Tellme. Studio
- Quack.com QXML Development Environment.
- AIML
- SALT
[edit] Notable Systems
See http://www.cs.cmu.edu/~dbohus/SDS/, http://www.ling.gu.se/~sl/dialogue_links.html, and http://www.disc2.dk/tools/opSLDSs.html.
[edit] Academics
The study of dialog systems is commonly considered a branch of human-computer interaction, although its origins are generally rooted in the automatic speech recognition community. Current trends are putting more research emphasis on aspects of psychology and linguistics.
[edit] Topics
- human-computer interaction
- linguistics
- computational linguistics
- discourse analysis
- pragmatics
- semantics
- parsing
- Symbol grounding
- language modeling
- multi-modal fusion
- multi-modal fission
- spoken language understanding
- psychology
- psycholinguistics
- human communication
- automatic speech recognition
- text-to-speech
- error handling
- dialog management
- affective dialog
- user modeling
- dialog engineering
- embodied communication
[edit] Conferences
[edit] Related Conferences
- Interspeech
- The International Conference on Multi-modal Interaction (ICMI)
- The Association for Computational Linguistics (ACL)
- The American Association for Artificial Intelligence (AAAI)
- Intelligent User Interfaces (IUI)
- Computer Human Interaction (CHI)
- The North American Association for Computational Linguistics (NAACL)
- SemDial
- The International Workshop on Robot and Human Interaction (ROMAN)
- Human Robot Interaction (HRI)
- Interact
- Spoken Language Technology, SLT
- Text, Speech, and Discourse (TSD)
- Empirical Methods in Natural Language Processing (EMNLP)
- Human Language Technology (HLT)
- The International Joint Conference on Artificial Intelligence (IJCAI)
- The International Conference on Computational Linguistics (COLING)
- Automatic Speech Recognition and Understanding (ASRU)
[edit] Related Journals
Historically, there were no journals devoted specifically to dialog systems. To address this need the Journal of Dialog Systems has been launched: the first journal dedicated particularly to dialog systems, with the goal of becoming the premiere international journal in the field.
There are also a number of related journals that often have dialog systems articles.
- ACM Transactions on Speech and Language Processing
- Computers, Speech, and Language
- Journal of Cognitive Systems Research
- IEEE Transactions on Systems, Man, and Cybernetics
- Computational Linguistics
- Cognitive Science
- International Journal of Speech Technology
- User Modeling and User-Adapted Interaction
- Natural Language Engineering
- Computers in Human Behavior
- ACM Transactions on Computer Human Interaction
[edit] Books
- Dialogue Processing in Spoken Language Systems
- Voice User Interface Design
- Spoken Dialogue Technology: Towards the Conversational Interface
- Machine Conversations
[edit] See also
- http://www.disc2.dk/
- The TALK project: on multimodal dialogue systems