@inproceedings{GaertnerKleinkopfAndresenetal.2021, author = {Markus G{\"a}rtner and Felicitas Kleinkopf and Melanie Andresen and Sibylle Hermann}, title = {Corpus reusability and copyright - challenges and opportunities}, series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-9) 2021. Limerick, 12 July 2021 (Online-Event)}, editor = {Harald L{\"u}ngen and Marc Kupietz and Piotr BaƄski and Adrien Barbaresi and Simon Clematide and Ines Pisetta}, publisher = {Leibniz-Institut f{\"u}r Deutsche Sprache}, address = {Mannheim}, doi = {10.14618/ids-pub-10470}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104700}, pages = {10 -- 19}, year = {2021}, abstract = {Making research data publicly available for evaluation or reuse is a fundamental part of good scientific practice. However, regulations such as copyright law can prevent this practice and thereby hamper scientific progress. In Germany, text-based research disciplines have for a long time been mostly unable to publish corpora made from material outside of the public domain, effectively excluding contemporary works. While there are approaches to obfuscate text material in a way that it is no longer covered by the original copyright, many use cases still require the raw textual context for evaluation or follow-up research. Recent changes in copyright now permit text and data mining on copyrighted works. However, questions regarding reusability and sharing of such corpora at a later time are still not answered to a satisfying degree. We propose a workflow that allows interested third parties to access customized excerpts of protected corpora in accordance with current German copyright law and the soon to be implemented guidelines of the Digital Single Market directive. Our prototype is a very lightweight web interface that builds on commonly used repository software and web standards.}, language = {en} }