Paper: Generating From A Deep Structure

ACL ID C90-2022
Title Generating From A Deep Structure
Venue International Conference on Computational Linguistics
Session Main Conference
Year 1990
  • Claire Gardent (University of Edinburgh, Edinburgh UK; University of Clermont-Ferrand 2, Clermont-Ferrand France)
  • Agnes Plainfosse (Laboratoires de Marcoussis, Marcoussis France)

Noncanonical semantic representations are representations which cannot be derived by some grammar G although they are semanticMly equivalent to representations which can be derived by G. This paper presents a generation Mgorithm which deals with non- canonical input. The proposed approach also enhances portability and language independence in that (i) linguis- tic decisions made by independent modules (e.g. , planner, transfer component) can be communicated to the gener- ater in a naturM way and (ii) the same algorithm coupled with different grammars will yield sentences in the cor- responding languages.