Steven Gillis

TL;DR: In this article, a memory-based approach to part-of-speech tagging is proposed, which is a form of supervised learning based on similarity-based reasoning, where the tagger-generator automatically builds a tagger which is able to tag new text the same way.

TL;DR: A large-scale application of the memory-based approach to part of speech tagging is shown to be feasible, obtaining a tagging accuracy that is on a par with that of known statistical approaches, and with attractive space and time complexity properties when using IGTree, a tree-based formalism for indexing and searching huge case bases.

TL;DR: The earlier the implantation took place, the smaller the delay was in comparison with normally hearing children with regard to the onset of prelexical babbling and with regard with auditory performance as measured by CAP.

TL;DR: A data-oriented (empiricist) alternative to the currently pervasive (nativist) Principles and Parameters approach to the acquisition of stress assignment is investigated and a similarity-based algorithm is used to learn the system of main stress assignment in Dutch.

TL;DR: This paper proposed a new methodology for determining the relationship between child-directed speech and child speech in early acquisition, and demonstrated the use of this methodology in investigati cation of early acquisition.