The Ins and Outs of Dutch noun countability classification

The Ins and Outs of Dutch Noun Countability Classification Timothy Baldwin CSLI Stanford University Stanford, CA 94305 USA tbaldwin@csli.stanford.edu Leonoor van der Beek University of Groningen Pb 716, 9700 AS, Groningen The Netherlands vdbeek@let.rug.nl Abstract This paper presents a range of methods for classifying Dutch noun countability based on either Dutch or English data. The classification is founded on transla- tional equivalences and the corpus anal- ysis of linguistic features which corre- late with particular countability classes. We show that crosslingual classification on the basis of word-to-word or feature- to-feature mappings between English and Dutch performs at least as well as in-language classification based on gold-standard Dutch countability data. 1 Introduction The performance of supervised learning methods is conditioned on the quality of annotation and also volume of training data (Hastie et al., 2001). This effect is felt particularly keenly in tasks of high feature dimensionality or low feature–class correlation. In many cases, high-quality data is not available in large quantities, but a large volume of lower-quality data can be accessed (Mitchell, 1999; Banko and Brill, 2001). Al- ternatively, high-quality data may exist for some parallel task which can be adapted to the task at hand through a lossy feature mapping. This strat- egy has been adopted successfully in NLP appli- cations such as part-of-speech tagging involving languages with a relative paucity of language re- sources or annotated data (Yarowsky et al., 2001; Cucerzan and Yarowsky, 2002). This paper takes a supervised learning task and contrasts the use of a restricted volume of in- language training data with the use of a larger vol- ume of out-of-language training data adapted to the task through a lossy mapping. Our aim in this is to determine the most effective fast-track solu- tion when faced with a novel task in a given lan- guage for which high-quality annotated data ex- ists in a closely-related language. We illustrate this issue by way of a type-level noun countability classification task in Dutch for which we have moderate amounts of high-quality annotated data in English and large amounts of medium-quality annotated data in Dutch (see §2.4). For English, previous research has shown that corpus evidence can be applied successfully to classify unannotated noun types for count- ability (Baldwin and Bond, 2003a; Baldwin and Bond, 2003b). We extend this research to Dutch and address the question of which of high-quality out-of-language English data and lower-quality in-language Dutch data produces the best Dutch countability classification results, realising that the feature mapping from English-to-Dutch in the first case will necessarily be lossy. We treat noun countability as a lexical prop- erty that determines determiner co-occurrence, the ability to pluralise, and enumeration effects. Each Dutch noun type is classified as being count- able and/or uncountable, noting that different senses/usages of a given word can occur with different countabilities, cf. I want a rabbit ⇀ ↽ Ik will een konijn [countable] vs. I would like some more rabbit, please ⇀ ↽ I zou graag nog wat konijn willen [uncountable]. Knowledge of …

Content truncated to 500 words