Dialogue system

Last updated

An automated online assistant on a website - an example where dialogue systems are major components Automated online assistant.png
An automated online assistant on a website - an example where dialogue systems are major components

A dialogue system, or conversational agent (CA), is a computer system intended to converse with a human. Dialogue systems employed one or more of text, speech, graphics, haptics, gestures, and other modes for communication on both the input and output channel.

Contents

The elements of a dialogue system are not defined because this idea is under research,[ citation needed ] however, they are different from chatbot. [1] The typical GUI wizard engages in a sort of dialogue, but it includes very few of the common dialogue system components, and the dialogue state is trivial.

Background

After dialogue systems based only on written text processing starting from the early Sixties, [2] the first speaking dialogue system was issued by the DARPA Project in the US in 1977. [3] After the end of this 5-year project, some European projects issued the first dialogue system able to speak many languages (also French, German and Italian). [4] Those first systems were used in the telecom industry to provide phone various services in specific domains, e.g. automated agenda and train tables service.

Components

What sets of components are included in a dialogue system, and how those components divide up responsibilities differs from system to system. Principal to any dialogue system is the dialogue manager, which is a component that manages the state of the dialogue, and dialogue strategy. A typical activity cycle in a dialogue system contains the following phases: [5]

  1. The user speaks, and the input is converted to plain text by the system's input recogniser/decoder, which may include:
  2. The text is analysed by a natural language understanding (NLU) unit, which may include:
  3. The semantic information is analysed by the dialogue manager, which keeps the history and state of the dialogue and manages the general flow of the conversation.
  4. Usually, the dialogue manager contacts one or more task managers, that have knowledge of the specific task domain.
  5. The dialogue manager produces output using an output generator, which may include:
  6. Finally, the output is rendered using an output renderer, which may include:

Dialogue systems that are based on a text-only interface (e.g. text-based chat) contain only stages 2–5.

Types of systems

Dialogue systems fall into the following categories, which are listed here along a few dimensions. Many of the categories overlap and the distinctions may not be well established.

Performance

Some authors measure the dialogue system's performance in terms of the percentage of sentences completely right, by comparing the model of sentences (this measure is called Concept Sentence Accuracy [6] or Sentence Understanding [4] ).

Applications

Dialogue systems can support a broad range of applications in business enterprises, education, government, healthcare, and entertainment. [7] For example:

In some cases, conversational agents can interact with users using artificial characters. These agents are then referred to as embodied agents.

Toolkits and architectures

A survey of current frameworks, languages and technologies for defining dialogue systems.

Name & linksSystem typeDescriptionAffiliation[s]Environment[s]Comments
AIML Chatterbot languageXML dialect for creating natural language software agents Richard Wallace, Pandorabots, Inc.
ChatScript Chatterbot languageLanguage/Engine for creating natural language software agents Bruce Wilcox
CSLU Toolkit
A state-based speech interface prototyping environment OGI School of Science and Engineering
M. McTear
Ron Cole
publications are from 1999.
NLUI Server [ usurped ]Domain-independent toolkitComplete multilingual framework for building natural language user interface systems LinguaSys out-of-box support of mixed-initiative dialogues
OlympusComplete framework for implementing spoken dialogue systems Carnegie Mellon University
Nextnova Multimodal PlatformPlatform for developing multimodal software applications. Based on State Chart XML (SCXML) Ponvia Technology, Inc.
VXML
Voice XML
Spoken dialogueMultimodal dialogue markup languageDeveloped initially by AT&T, then administered by an industry consortium and finally a W3C specificationExampleprimarily for telephony.
SALT markup languageMultimodal dialogue markup language Microsoft "has not reached the level of maturity of VoiceXML in the standards process".
Quack.com - QXMLDevelopment EnvironmentCompany bought by AOL
OpenDial Domain-independent toolkitHybrid symbolic/statistical framework for spoken dialogue systems, implemented in Java University of Oslo
NADIA dialogue engine and dialogue modellingCreating natural dialogues/dialogue systems. Supports dialogue acts, mixed initiative, NLG. Implemented in Java.Markus M. Bergcreate XML-based dialogue files, no need to specify grammars, publications are from 2014

See also

References

  1. Klüwer, Tina. "From chatbots to dialog systems." Conversational agents and natural language interaction: Techniques and Effective Practices. IGI Global, 2011. 1-22.
  2. McTear, Michael, Zoraida Callejas, and David Griol, The conversational interface: Talking to smart devices , Springer, 2016.
  3. Giancarlo Pirani (ed), Advanced algorithms and architectures for speech understanding , Vol. 1. Springer Science & Business Media, 2013.
  4. 1 2 Alberto Ciaramella, A prototype performance evaluation report, Sundial work package 8000 (1993).
  5. Jurafsky & Martin (2009), Speech and language processing. Pearson International Edition, ISBN   978-0-13-504196-3, Chapter 24
  6. Bangalore, Srinivas, and Michael Johnston. "Robust understanding in multimodal interfaces." Computational Linguistics 35.3 (2009): 345-397.
  7. Lester, J.; Branting, K.; Mott, B. (2004), "Conversational Agents" (PDF), The Practical Handbook of Internet Computing, Chapman & Hall
  8. Crovari; Pidò; Pinoli; Bernasconi; Canakoglu; Garzotto; Ceri (2021), "GeCoAgent: a conversational agent for empowering genomic data extraction and analysis", ACM Transactions on Computing for Healthcare, 3, ACM New York, NY: 1–29, doi:10.1145/3464383, hdl: 11311/1192262 , S2CID   245855725

Further reading