LuNa Corpus Tools
LuNa’s functionality is to tokenize and to standardize a text written in Luxembourgish, e.g., if orthographic variations for words appear. Additionally, LuNa foresees a tagging of words using a POS Tagger. To analyze a text, LuNa supports the search of word formation affixes as well as the annotation of them as such. In the context of the annotation process of word formation affixes, some other analysis can be carried out, for example the analysis of morphological productivity, or the search of the stems of the words with word formation suffixes in the entire corpus. Also, LuNa offers a simple lemmatization for the Luxembourgish language. Several approaches have been investigated, and a hybrid (rule-based and statistical) lemmatizer is chosen because of its prominent performance for Luxembourgish language. Beside data processing components, first implementations in view of a sentiment analysis and topic modeling exist.
Download and try the toolIn order to use the tool, please unzip the file and try to start LunaCorpusTools.jar file. Please note that you need the an actual version of Java Virtual Machine in order to run the program. For eventuel problems try to lunch the program with "java -jar LunaCorpusTools.jar" over the command line, in order to see posibble warnings and errors. To see the source code of the LunaCorpusTools visit my repos on github
Michel Rodange Portal
Michel Rodange Portal is a digital edition of the work of the national Luxembourgish poet Michel Rodange enriched with additional text critical annotations.
Visit the portal Michel-Rodange-Portal
Small coding projects
For some small coding projects vistit my repos on github
About Me
I earned my master’s degree in Computational Philology from the University of Würzburg (Germany) and my PhD in Digital Humanities from the University of Trier (Germany). Since 2012 I have been involved in different projects at the Universities of Trier and Luxembourg. I am interested in research on appling machine learning in different fields of Humanities. These could be big databases, corpora, portals or language corpora and big language models, especially the ones which were created with the help of the newest deep learning algorithms.
Additional Information
I am about to finish my book about Artificial Intelligence