STO: A Danish Lexicon Resource - Ready for Applications

$EVWUDFWW This paper deals with the STO lexicon, the most comprehensive computational lexicon of Danish developed for NLP/HLT applications, which is now ready for use. Danish was one of the 12 EU-languages participating in the LE-PAROLE and SIMPLE projects; therefore it was obvious to continue this work building on our experience obtained from these projects. The material for Danish produced within these projects – further enriched with language-specific information-is incorporated into the STO lexicon. First, we describe the main characteristics of the lexical coverage and linguistic content of the STO lexicon; second, we present some recent uses and point to some prospective exploitations of the material. Finally, we outline an internet-based user interface, which allows for browsing through the complex information content of the STO lexical database and some other selected WRL's for Danish. 3URMHFW2EMHFWLYHVDQGG%DFNJURXQGG The objective of the Danish STO project (SprogTeknologisk Ordbase, i.e. Lexical Database for Language Technology) was twofold: first, to develop a flexible, large-scale lexical resource in order to remedy a general bottleneck problem for Danish NLP applications; second, to strengthen the position of Danish, as a member of the still growing multilingual NLP/HLT community. The project background as well as various development aspects and stages were presented at previous LREC 1. STO was a national collaborational project, initiated by CST and founded on a contract with the Danish Ministry for Science, Technology and Development. The duration of the project was three years, ending February 2004. STO is well integrated with the European activities in the field of computational lexicon development for the following reasons. Danish was one of the 12 EU-languages that were part of the PAROLE (LE2-4017, 1996-98) and SIMPLE (LE4-8346, 1999-2000) projects. The LE-PAROLE/SIMPLE 2 models and descriptive methods obtained a status of being 'de facto standards' in the development of computational lexicons (Lenci et al, 2000). It was obvious to continue this work and build on our experience gathered from these multilingual projects, the more so as other national projects, e.g. the Italian CLIPS (Ruimy et al, 2002) were started on the same basis. Even though in STO a number of language-specific refinements, various adaptations and extensions are implemented, its model and descriptive method is kept compatible with the architecture and descriptive language shared by the lexicons developed within the PAROLE/SIMPLE framework. Therefore the STO lexicon can be linked to other lexicons that share the same features and can be exploited in …