%0 Conference Paper %1 Gaertne/etal:2021 %A Gärtner, Markus %A Kleinkopf, Felicitas %A Andresen, Melanie %A Hermann, Sibylle %B Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-9) 2021. Limerick, 12 July 2021 (Online-Event) %C Mannheim %D 2021 %E Lüngen, Harald %E Kupietz, Marc %E Bański, Piotr %E Barbaresi, Adrien %E Clematide, Simon %E Pisetta, Ines %I Leibniz-Institut für Deutsche Sprache %K lebenslauf myown publist ubprojekt xsample %P 10-19 %R 10.14618/ids-pub-10470 %T Corpus reusability and copyright - challenges and opportunities %U https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104700 %X 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.

@inproceedings{Gaertne/etal: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.}, added-at = {2022-04-24T16:39:52.000+0200}, address = {Mannheim}, author = {Gärtner, Markus and Kleinkopf, Felicitas and Andresen, Melanie and Hermann, Sibylle}, biburl = {https://puma.ub.uni-stuttgart.de/bibtex/21379876c8e44201273f877236280c71e/hermann}, doi = {10.14618/ids-pub-10470}, editor = {Lüngen, Harald and Kupietz, Marc and Bański, Piotr and Barbaresi, Adrien and Clematide, Simon and Pisetta, Ines}, interhash = {561f3d778c6cccefca678fedc2d802b6}, intrahash = {1379876c8e44201273f877236280c71e}, keywords = {lebenslauf myown publist ubprojekt xsample}, language = {en}, pages = {10-19}, publisher = {Leibniz-Institut für Deutsche Sprache}, series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-9) 2021. Limerick, 12 July 2021 (Online-Event)}, timestamp = {2022-05-13T14:41:26.000+0200}, title = {Corpus reusability and copyright - challenges and opportunities}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-104700}, year = 2021 }