@book{OPUS4-7522, title = {Proceedings of the LREC 2018 Workshop “Challenges in the Management of Large Corpora (CMLC-6)” 07 May 2018 – Miyazaki, Japan}, editor = {Piotr Bański and Marc Kupietz and Adrien Barbaresi and Hanno Biber and Evelyn Breiteneder and Simon Clematide and Andreas Witt}, publisher = {European language resources association (ELRA)}, address = {Paris}, isbn = {979-10-95546-14-6}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-75227}, pages = {VI, 36}, year = {2018}, abstract = {Contents: 1. Christoph Kuras, Thomas Eckart, Uwe Quasthoff and Dirk Goldhahn: Automation, management and improvement of text corpus production, S. 1 2. Thomas Krause, Ulf Leser, Anke L{\"u}deling and Stephan Druskat: Designing a re-usable and embeddable corpus search library, S. 6 3. Radoslav R{\´a}bara, Pavel Rychl{\´y} and Ondřej Herman: Distributed corpus search, S. 10 4. Adrien Barbaresi and Antonio Ruiz Tinoco: Using elasticsearch for linguistic analysis of tweets in time and space, S. 14 5. Marc Kupietz, Nils Diewald and Peter Fankhauser: How to Get the Computation Near the Data: Improving data accessibility to, and reusability of analysis functions in corpus query platforms, S. 20 6. Roman Schneider: Example-based querying for specialist corpora, S. 26 7. Paul Rayson: Increasing interoperability for embedding corpus annotation pipelines in Wmatrix and other corpus retrieval tools, S. 33}, language = {en} }