Sussi Olsen

Current research

• Technological language resources, morphological, syntactic and semantic
• Annotation of linguistic resources
• Computational lexicography
• Corpus linguistics
• Validation of linguistic resources

Knowledge of languages

CV

Education: Masters degree in Spanish and Computational Linguistics at University of Copenhagen.

Since 1997 employed at Center for Sprogteknologi, University of Copenhagen, as a research associate.

Research projects and tasks: 

2018 -> Part of the ELEXIS project that fosters cooperation and knowledge exchange between lexicographic communities within EU and to make lexicographic data available for language technology. 

2017-> Part of the EU project eTranslation TermBank collecting terminology for the EU translation platform.

2017 -> Part of the EU project ELRC that collects language data relevant to public institutions for the EU translation platform that is open to public institutions.  

2016 -17 Part of the CLARIN⁺ project (EU) dealing with identifying new CLARIN partners

2016-17 Part of a collaborational project with The Society for Danish Language and Literature with the aim of developing a lemmatiser and a pos tagger for 19th century Danish.

2015-17 Part of the EU project Language Technology Observatory, mainly engaged in identifying language resources for machine translation

2013-17 Part of project Semantic Processing across Domains. especially involved in semantic annotation of corpora.

Deltager i DigHumLab-projektet med forskelligartede opgaver

2012-2015 Part of the Nordic network LUNAS focusing on academic language use in the Nordic countries

From 2011 - 2013 participating in the EU project META-NORD mainly working with data collection and specification of subject domains.                         

From 2010 participating in the EU project LetsMT!

From 2008 till 2010 responsible for the work package 2.2 in the DK-CLARIN project, with the aim of compiling a 11 m. sub-corpus of language for special purposes. The corpus will be PoS-tagged and annotated with term status information.
Participated in the DAD project (2007-2009, funded by FKK) dealing with annotation of abstract anaphors and their references in written and spoken corpora.
From 2004 and ongoing validator of various lexicon and corpus projects, e.g. the EuroWordnet for ELRA and the national Dutch corpus. Supervisor for validators for all kinds of languages.
Participated in the SIMPLE-DK project in 2000 working with ontologically structured vocabularies.
From 1997-2004 mainly working at the computational lexicon project STO where the principal research and working areas have been the administration of the domain specific text corpora and the selection of the vocabularies from these, the treatment of multiword concepts along with the syntactic structuring of the vocabulary. Still doing updates and giving courses on STO.