I participated in the following projects:
Allegro is an EU funded INTERREG IV A project which focuses on the development of new technologies for foreign language learning. Its aim is to make computer-based foreign language learning more interactive, more engaging, and more fun! It provides learners with tools which would enable them to exercise practical conversations, which they might encounter in real life, with a computer. I work at modeling the linguistic and lexical knowledge and its interface with the domain (ontological) knowledge base.
SEMbySEM is a European EUREKA ITEA2 research project involving several industrial and academic institutions and funded by national authorities. It aims to provide a software system dedicated to the monitoring and management of systems of all sizes. Talaris is concerned with the multilingual linguistic aspects pertaining to the representation and visualisation of the underlying semantic knowledge base.
Automated Semantic Classification of French Verbs
The topic of my master thesis was to attempt a classification of French verbs using Formal Concept Analysis. My supervisors were Claire Gardent and Fabienne Venant. I developed some Perl modules to convert between input and output formats of various FCA tools. These modules are unfortunately not yet ready to be shared and uploaded to CPAN. Drop me a mail if you want to try them anyway.
Relate French synonyms to a dictionary sense of their synonym
This was a part of the Nancy Masters in Computational Linguistics: Lexical Enrichment of the FMA Ontology with French synonym terms - with Nadiya Yampolska and Charif Alchiekh Haydar and under supervision of Claire Gardent and Paul Buitelaar.
SynLex: a syntactic lexicon for French
The LADL tables are an exhaustive, empirically-based syntax-based lexicon of French (a "lexicon-grammar"), initiated by Maurice Gross. We are working on a method (and its implementation) to convert these tables into a format more suitable for automated NLP. (See here and here and also here for details.)
Conversion of print documents to electronic text
With READ: Automating the structural markup process in the conversion of print documents to electronic text; possible benefits of using XML standards at the digitization of the
Trévoux dictionary (See here and here for details.)
French Wordnet: Perl scripts to convert the text dump of a EuroWordNet database (which comes with the EuroWordNet distribution when you buy it) into a Berkeyley DB, so that it can be queried via the Lingua::Wordnet CPAN module by Dan Brian (details & download).
... and also
Layout edit for the e-journal DMTCS.
I'm experimenting with turning a computer linguistic application into a Grid service using OGSI::Lite, an OGSI implementation in Perl featuring among others one of the very first implementations of WSRF.
Morphalou, an open source morphological XML lexicon for French, with 68075 lexical entries and 539413 inflected forms.