Lonneke van der Plas

Learn More
We describe Joost, our QA system for Dutch, which makes extensive use of dependency relations. We analyzed the full Dutch CLEF QA corpus syntactically and mined it off-line for information that may be useful for QA. Joost answers questions either by table look-up, or by searching for answers in paragraphs returned by an IR engine. In both cases, dependency(More)
Broad-coverage semantic annotations for training statistical learners are only available for a handful of languages. Previous approaches to cross-lingual transfer of semantic annotations have addressed this problem with encouraging results on a small scale. In this paper, we scale up previous efforts by using an automatic approach to semantic annotation(More)
There have been many proposals to extract semantically related words using measures of distributional similarity, but these typically are not able to distinguish between synonyms and other types of semantically related words such as antonyms, (co)hyponyms and hypernyms. We present a method based on automatic word alignment of parallel corpora consisting of(More)
We describe our system for the monolingual Dutch and multilingual English to Dutch QA tasks. First, we give a brief outline of the architecture of our QA-system, which makes heavy use of syntactic information. Next, we describe the modules that were improved or developed esepcially for the CLEF tasks, i.e. (1) incorporation of syntactic knowledge in the(More)
Semantic role labels are the representation of the grammatically relevant aspects of a sentence meaning. Capturing the nature and the number of semantic roles in a sentence is therefore fundamental to correctly describing the interface between grammar and meaning. In this paper, we compare two annotation schemes, PropBank and VerbNet, in a task-independent,(More)
We describe our system for the monolingual Dutch and multilingual English to Dutch QA tasks. First, we give a brief outline of the architecture of our QA-system, which makes heavy use of syntactic information. Next, we describe the modules that were improved or developed esepcially for the CLEF tasks, i.e. (1) incorporation of syntactic knowledge in the(More)
In this article, we examine the variation of the predicate-argument structure between English and French in an experimental and data-driven approach. We annotate a corpus of 1000 French sentences with predicate-argument structure using a framework originally developed for English. We identify a number of non-matching predicates and examine them in a(More)
The goal of automatic term extraction often is not so much the creation of a new list of domain specific terms, but rather the (semi-) automatic extension of a list of known terms. In this paper, we focus on the use of existing terms from glossaries, thesaurus, or ontologies to extract new terms from a domain specific text. Our new method is used to extract(More)