Natural Language Generation from Concept Blends



Conceptual Blending (CB) is a framework for the integration of knowledge from different sources onto one,
known as the blend. For example, the concept ?edutainment? is the blend of ?education? and ?entertainment?.
This paper presents an approach on producing a natural language reading of the blends that are generated by
Divago, a system that applies a computational implementation of CB to transform a search space. Represented
through a semantic network (the concept map), the blend demands considerable effort in its interpretation.
Obtaining its Natural Language description raises several issues and is an interesting challenge for the field of
Natural Language Generation. In this paper, we propose a reading based on diagnostic features with respect
to a reference concept. We make some reflections on the choice of these references, namely regarding the
creative potential associated.


Natural Language Generation


Conceptual Blending


AISB'03 Symposium on Creativity in Arts and Sciences, April 2003

Cited by

Year 2005 : 1 citations

 "Exploring Creative Concepts in the Nearest Neighborhood using Lexical Ontologies", Prasad Pingali, Jagarlamudi Jagadeesh, Vasudeva Varma, Bipin Indurkhya. Indian International Conference on Artificial Intelligence 2005, December 2005.

Year 2004 : 2 citations

 Pedro A. Gonzalez Calero. Arcano: Case-Based Framework Documentation and their Example-Based Learning. In proceedings of Jornada de Seguimiento de Proyectos, 2004. Programa Nacional de Tecnologıas Informaticas. UCM, Madrid 2004.

 Stavros Papadakis. "Pun Generation via Conceptual Blending", MSc Dissertation. Imperial College London, 2004.