@article{MargarethaLuengen2014, author = {Eliza Margaretha and Harald L{\"u}ngen}, title = {Building linguistic corpora from Wikipedia articles and discussions}, series = {Journal of Language Technology and Computational Linguistics. Special issue on building and annotating corpora of computer-mediated communication. Issues and challenges at the interface between computational and corpus linguistics}, volume = {29}, number = {2}, editor = {Michael Bei{\"s}wenger and Angelika Storrer and Nelleke Oostdijk and Henk van den Heuvel}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-33306}, pages = {59 -- 82}, year = {2014}, abstract = {Wikipedia is a valuable resource, useful as a lingustic corpus or a dataset for many kinds of research. We built corpora from Wikipedia articles and talk pages in the I5 format, a TEI customisation used in the German Reference Corpus (Deutsches Referenzkorpus - DeReKo). Our approach is a two-stage conversion combining parsing using the Sweble parser, and transformation using XSLT stylesheets. The conversion approach is able to successfully generate rich and valid corpora regardless of languages. We also introduce a method to segment user contributions in talk pages into postings.}, language = {de} }