A Constructionist Approach to Grammar Inference
Oskar Kohonen, Sámi Virpioja, Krista Lagus · 2009
Models based on Chomskian grammar are not as pervasive in certain NLP applications as might be expected from their status in linguistics, comparing to, e.g., statistical n-gram models or vector space models. In this paper, we look at grammar inference from a viewpoint of constructionist theories of language, which are in contrast to the Chomskian tradition, and avoid the separation of morphology, syntax, semantics and pragmatics. We consider the utility of constructionist theories in NLP applications, present a computational framework for learning constructions, and discuss related experimental work. 1