Alpino is a wide-coverage computational analyzer of Dutch which aims at accurate, full, parsing of unrestricted text. We describe the head-driven lexicalized grammar and the lexical component, which has been derived from existing resources. The grammar produces dependency structures, thus providing a reasonably abstract and theory-neutral level of linguistic representation. An important aspect of wide-coverage parsing is robustness and disambiguation. The dependency relations encoded in the dependency structures have been used to develop and evaluate both hand-coded and statistical disambiguation methods.

this paper, we combine different systems employing known representations. The observation that suggests this approach is that systems that are designed differently, either because they use a different formalism or because they contain different knowledge, will typically produce different errors. We hope to make use of this fact and reduce the number of errors with very little additional effort by exploiting the disagreement between different language models. Al- though the approach is applicable to any type of language model, we focus on the case of statistical disambiguators that are trained on annotated corpora. The examples of the task that are present in the corpus and its annotation are fed into a learning algorithm, which induces a model of the desired input-output mapping in the form of a classifier. * EO. Box 9103, 6500 HD Nijmegen, The Netherlands, hvh@let.ktm.nl t Universiteitsplein 1, 2610 Wilrijk, Belgium, {zavrel, daelem}@uia.ua.ac.be () 2000 Association for Computational Linguistics We use a number of different learning algorithms simultaneously on the same training corpus. Each type of learning method brings its own 'inductive bias' to the task and will produce a classifier with slightly different characteristics, so that different methods will tend to produce different errors

Lexical ambiguity is an important source of inefficiency for wide-coverage HPSG parsing. In this paper, we propose a lexical analysis filter which removes unlikely lexical categories. The filter is implemented as a straightforward HMM n-gram POS-tagger, which computes the 'a posteriori' probability of each lexical category. A lexical category is removed if a competing lexical category is sufficiently more likely. The novel aspect of our approach is the fact that the tagger is trained on the output of the parser itself; therefore there is no need for hand-annotated material. Use of this filter increases the speed of the parser considerably, and in addition gives rise to an improvement in parsing accuracy.

This paper describes a new method, COMBI-BOOTSTRAP, to exploit existing taggers and lexical resources for the annotation of corpora with new tagsets. COMBI-BOOTSTRAP uses existing resources as features for a second level machine learning module, that is trained to make the mapping to the new tagset on a very small sample of annotated corpus material. Experiments show that COMBI-BOOTSTRAP: i) can integrate a wide variety of existing resources, and ii) achieves much higher accuracy (up to 44.7 % error reduction) than both the best single tagger and an ensemble tagger constructed out of the same small training sample.

(Note: due to a formatting problem, some of the pages only appear to be missing text.)

Abstract not found

One of the central assumptions of Optimality Theory is the hypothesis of strict domination among constraints. A few studies have suggested that this hypothesis is too strong and should be abandoned in favor of a weaker cumulativity hypothesis. If this suggestion is correct, we should be able to find evidence for cumulativity in the comprehension of Gapping sentences, which lack explicit syntactic clues in the form of the presence of a finite verb. On the basis of a comparison between several computational models of constraint evaluation, we conclude that the comprehension of Gapping sentences does not yield compelling evidence against the strict domination hypothesis. 1

treebank study comparing spoken and written language