How the statistical revolution changes (computational) linguistics

Abstract

This paper discusses some of the ways that the “statistical revolution” has changed and continues to change the relationship between linguistics and computational linguistics. I claim that it is more useful in parsing to make an open world assumption about possible linguistic structures, rather than the closed world assumption usually made in grammar-based approaches to parsing, and I sketch two different ways in which grammar-based approaches might be modified to achieve this. I also describe some of the ways in which probabilistic models are starting to have a significant impact on psycholinguistics and language acquisition. In language acquisition Bayesian techniques may let us empirically evaluate the role of putative universals in universal grammar.