Architectures for Natural Language Generation: Problems and Perspectives

  title={Architectures for Natural Language Generation: Problems and Perspectives},
  author={Koenraad De Smedt and Helmut Horacek and Michael Zock},
Current research in natural language generation is situated in a computational linguistics tradition that was founded several decades ago. We critically analyse some of the architectural assumptions underlying existing systems and point out some problems in the domains of text planning and lexicalization. Guided by the identification of major generation challenges viewed from the angles of knowledge-based systems and cognitive psychology, we sketch some new directions for future research. 
Highly Cited
This paper has 52 citations. REVIEW CITATIONS

From This Paper

Figures, tables, results, connections, and topics extracted from this paper.
35 Extracted Citations
120 Extracted References
Similar Papers

Citing Papers

Publications influenced by this paper.

52 Citations

Citations per Year
Semantic Scholar estimates that this publication has 52 citations based on the available data.

See our FAQ for additional information.

Referenced Papers

Publications referenced by this paper.
Showing 1-10 of 120 references

Text generation: The problem of text structure

  • W. Mann
  • D. McDonald & L. Bolc (Eds.), Natural language…
  • 1988
Highly Influential
4 Excerpts

POPEL – A parallel and incremental natural language generation system

  • N. Reithinger
  • C.L. Paris, W.R. Swartout & W.C. Mann (Eds…
  • 1991
Highly Influential
8 Excerpts

Generating language with a phrasal lexicon

  • E. Hovy
  • D. McDonald & L. Bolc (Eds.), Natural Language…
  • 1988
Highly Influential
8 Excerpts

Generating natural language under pragmatic constraints

  • E. Hovy
  • Hillsdale, NJ: Earlbaum.
  • 1988
Highly Influential
8 Excerpts

Incremental syntactic and phonological encoding: An outline of the Synphonics formulator

  • B. Abb, C. Guenther, M. Herweg, K. Lebeth, C. Maienborn, A. Schopp
  • 1995
3 Excerpts

Similar Papers

Loading similar papers…