Deep Generation — LT World

LT World

Supporters

provided by

dfki logo

with support by

eu star logofp7 logo

through

meta logo
clarin logo

as well as by

bmbf logo

through

take logo

N.B.

This site uses Google Analytics to record statistics about site visits - see Legal Information.

You are here: Home kb Information & Knowledge Technologies Deep Generation

Deep Generation


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.


http://www.lt-world.org/hlt_survey/ltw-chapter4-3.pdf



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.