home kb Information and Knowledge Technologies Natural Language Generation Natural Language Generation
External Links
Google
Google Scholar
Citeseer
provided by
German Research Center for Artificial Intelligence
with support by
through
as well as by
through
 

Natural Language Generation

abbreviation(s): NLG
definition: Natural Language Generation (NLG) is concerned with turning some usually non-linguistic representation of information and intended effect into fluent text preserving both meaning and intention.

NLG systems often identify the content to be verbalized. They structure the document into interrelated sentence-sized chunks, choose appropriate words, aggregate and elide information to ensure fluency, create contextually appropriate referring expressions, such as pronouns, and follow grammatical constraints of the chosen language. All this is achieved using knowledge about the world and the domain of dicsourse, about communication and about languages.

NLG components are used for e.g. automatic report generation, document authoring, dialogue, concept-to-speech, multi-modal and machine translation systems.

Evaluating the correctness and the appropriateness of generated text is a research theme on its own since there is usually no single correct solution. One important way to tackle the problem consists in creating reference corpora and performing shared evaluation tasks, e.g. on generating referring expressions. However, this is not intended to replace less formal evaluation strategies such as human assessments.

See also the corresponding HLT Survey chapter: http://www.lt-world.org/HLT_Survey/ltw-chapter4-1.pdf
related project(s):
  • Multimedia Abstract Generation for Intensive Care (MAGIC)
  • Transnational Environmental Management Support & Information System (TEMSIS)
  • A Reference Architecture for Generation Systems (RAGS)
  • IDAS
  • KPML
  • Smoking Termination with cOmputerised Personalisation (STOP)
  • What You See Is What You Meant (WYSIWYM)
related organisation(s):
  • Special Interest Group on Generation (SIGGEN)
  • Natural Language Generation Group at the Department of Computing Science, University of Aberdeen (NLG Group Aberdeen)
  • Natural Language Technology Group (NLTG)
  • University of Aberdeen
  • Institute for Communicating and Collaborative Systems (ICCS)
  • German Research Center for Artificial Intelligence (DFKI)
  • CoGenTex, Inc.
  • Columbia Natural Language Processing Group
related person(s):
  • Anja Belz
  • Robert Dale
  • Johanna D. Moore
  • Charles Callaway
  • Roger Evans
  • Manfred Stede
  • Michael White
  • Emiel Krahmer
  • Mariët Theune
  • Claire Gardent
  • David McDonald
  • Cecile L. Paris
  • Kees Van Deemter
  • Matthew Stone
  • Tilman Becker
  • John A. Bateman
  • Helmut Horacek
  • Michael Elhadad
  • Chris Mellish
  • Donia Scott
  • Ehud Reiter
  • Kathleen R. McKeown
  • Stephan Busemann
related system(s) / resource(s):
  • ProjectReporter
  • RealPro
  • TG/2
related publication(s):

Building Natural Language Generation Systems.
Reiter, Ehud and Dale, Robert.
Cambridge University Press. Cambridge UK. 2000.

Planning Text for Advisory Dialogues: Capturing Intentional and Rhetorical Information.
Johanna Moore and Cecile Paris.
Computational Linguistics. 19 (4). 1993. 651-694.

Text Generation: Using Discourse Strategies and Focus Constraints to Generate Natural Language Text.
Kathleen R. McKeown.
Cambridge University Press. Cambridge. 1985.

Generierung natürlichsprachlicher Texte.
Stephan Busemann.
Günther Görz, Claus-Rainer Rollinger, Josef Schneeberger. Künstliche Intelligenz. Oldenburg Verlag, München, Wien. 2000. 783-814.