Artificial data and language theory - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2005

Artificial data and language theory

Franck Thollard
  • Function : Author
  • PersonId : 837047


Tests on artificial data sets are important in order to systematically assess the merits and limits of learning algorithms. This requires that distributions over both the hypothesis space and the instance space be controlled, which, in turn, implies the definition of control parameters. This paper surveys the control parameters that have been used in the context of grammatical inference, and provides directions for further identification of relevant parameters.
No file

Dates and versions

inria-00119756 , version 1 (11-12-2006)


  • HAL Id : inria-00119756 , version 1


Antoine Cornuéjols, Franck Thollard. Artificial data and language theory. GI workshop 2006. Grammatical inference: workshop on open problems and new directions, Colin de la Higuera, Nov 2005, Saint-Etienne, France. ⟨inria-00119756⟩
52 View
0 Download


Gmail Facebook Twitter LinkedIn More