Deep Generation
synonym(s): In-Depth Generation
definition: A knowledge-based approach to natural language generation that stresses theoretical motivation and re-usability of technology and knowledge sources across tasks and domains of dicourse. Opposed to shallow generation, which emphasizes rapid application development at the cost of genericity. Deep generation can be subdivided into principled approaches to
- Document planning - the subdivision of information onto clause-sized chunks and the semantic and rhetorical structuring for presenting that information;
- Sentence planning - the choice of words, aggregation of information into linguistic units, and the generation of referring expressions;
- Surface generation - the realization of an actual text based on these decisions, including linearization, addition of closed class words, and morphological inflection. See also Syntactic Generation.
See also the corresponding HLT Survey chapter: http://www.lt-world.org/hlt_survey/ltw-chapter4-3.pdf
related project(s):
- Multimedia Abstract Generation for Intensive Care (MAGIC)
- IDAS
- KPML
- A Reference Architecture for Generation Systems (RAGS)
- What You See Is What You Meant (WYSIWYM)
related organisation(s):
- German Research Center for Artificial Intelligence (DFKI)
- Natural Language Technology Group (NLTG)
- Natural Language Generation Group at the Department of Computing Science, University of Aberdeen (NLG Group Aberdeen)
related person(s):
- Anja Belz
- Matthew Stone
- John A. Bateman
- Donia Scott
- Helmut Horacek
- Michael Elhadad
- Chris Mellish
- Tilman Becker
- Ehud Reiter
- Kathleen R. McKeown
- Cecile L. Paris
- Kees Van Deemter
- Robert Dale
- Johanna D. Moore
- Charles Callaway
- Richard Evans
- Manfred Stede
- Michael White
- Emiel Krahmer
- Mariët Theune
- Claire Gardent
- David McDonald
related system(s) / resource(s):
- ProjectReporter
- RealPro
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.
Moore, Johanna D. and Paris, Cécile L.
Computational Linguistics Vol 19, pp. 651-694. 1993.