Transformation-based learning of danish stress assignment

Transformation-Based Learning of Danish Grammar Correction

We describe a technique for using the Brill Tagger to learn to identify grammar errors. We have applied this technique to two types of Danish grammar errors: incorrect commas, and incorrect article-noun agreement. The system identi es comma errors with a precision of 91%, while agreement errors are identi ed with 95% precision, with many of the system errors resulting from de ciencies in the ta...

Transformation-Based Learning of Danish Grammar Corre tion

Commentary On Daelemans, Gillis, And Durieux

The authors turn an Instance-Based Learning model (IBL) loose on some Dutch stress data. They come to a number of conclusions regarding the models that could underlie human stress acquisition, to wit, " . . . tree building operations proposed in learning theories for metrical phonology are not necessary for learning stress assignment" (p. 449) One assumes that this conclusion carries over to gr...

Stress, pauses, pronominal types and pronominal functions in Danish spoken data

In this paper we present a study of the relation between types of third personal singular neuter pronoun and their functions in Danish spoken data where stress information is marked so that personal and demonstrative occurrences of the pronouns can be distinguished. This study confirms that there are language specific differences in the way various types of pronoun are used to refer to abstract...

The Acquisition of Stress: A Data-Oriented Approach

A data-oriented (empiricist) alternative to the currently pervasive (nativist) Principles and Parameters approach to the acquisition of stress assignment is investigated. A similaritybased algorithm, viz. an augmented version of Instance Based Learning is used to learn the system of main stress assignment in Dutch. In this non-trivial task a comprehensive lexicon of Dutch monomorphemes is used ...