@incollection{BeißwengerWighamEtienneetal.2017, author = {Beißwenger, Michael and Wigham, Ciara and Etienne, Carole and Fišer, Darja and Grumt Su{\´a}rez, Holger and Herzberg, Laura and Hinrichs, Erhard and Horsmann, Tobias and Karlova-Bourbonus, Natali and Lemnitzer, Lothar and Longhi, Julien and L{\"u}ngen, Harald and Ho-Dac, Lydia-Mai and Parisse, Christophe and Poudat, C{\´e}line and Schmidt, Thomas and Stemle, Egon W. and Storrer, Angelika and Zesch, Torsten}, title = {Connecting resources: Which issues have to be solved to integrate CMC corpora from heterogeneous sources and for different languages?}, booktitle = {Proceedings of the 5th Conference on CMC and Social Media Corpora for the Humanities (cmccorpora17). 3-4 October 2017, Eurac Research, Italy}, editor = {Stemle, Egon W. and Wigham, Ciara R.}, edition = {First edition}, url = {https://cmc-corpora2017.eurac.edu/proceedings/cmccorpora17-proceedings.pdf}, pages = {52 -- 55}, year = {2017}, abstract = {The paper reports on the results of a scientific colloquium dedicated to the creation of standards and best practices which are needed to facilitate the integration of language resources for CMC stemming from different origins and the linguistic analysis of CMC phenomena in different languages and genres. The key issue to be solved is that of interoperability - with respect to the structural representation of CMC genres, linguistic annotations metadata, and anonymization/pseudonymization schemas. The objective of the paper is to convince more projects to partake in a discussion about standards for CMC corpora and for the creation of a CMC corpus infrastructure across languages and genres. In view of the broad range of corpus projects which are currently underway all over Europe, there is a great window of opportunity for the creation of standards in a bottom-up approach.}, subject = {Korpus }, language = {en} }