@incollection{Schneider2018, author = {Roman Schneider}, title = {KoGra-DB: Using MapReduce for language corpora}, series = {Informatik 2013. Informatik angepasst an Mensch, Organisation und Umwelt}, editor = {Matthias Horbach}, publisher = {K{\"o}llen}, address = {Bonn-Buschdorf}, isbn = {978-3-88579-614-5}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-70363}, pages = {140 -- 142}, year = {2018}, abstract = {Linguistic query systems are special purpose IR applications. We present a novel state-of-the-art approach for the efficient exploitation of very large linguistic corpora, combining the advantages of relational database management systems (RDBMS) with the functional MapReduce programming model. Our implementation uses the German DEREKO reference corpus with multi-layer linguistic annotations and several types of text-specific metadata, but the proposed strategy is language-independent and adaptable to large-scale multilingual corpora.}, language = {en} }