@InProceedings{Schaefer2015b,
  Title                    = {Processing and querying large web corpora with the {COW14} architecture},
  Author                   = {Roland Schäfer},
  Booktitle                = {Proceedings of Challenges in the Management of Large Corpora 3 (CMLC-3)},
  Year                     = {2015},

  Address                  = {Lancaster},
  Editor                   = {Piotr Bański and Hanno Biber and Evelyn Breiteneder and Marc Kupietz and Harald Lüngen and Andreas Witt},
  Organization             = {UCREL},
  Publisher                = {IDS},

  Abstract                 = {In this paper, I present the COW14 tool chain, which comprises a web corpus creation tools called texrex, wrappers for existing linguistic annotation tools as well as an online query software called Colibri2 . By detailed descriptions of the implementation and systematic evaluations of the performance of the software on different types of systems, I show that the COW14 architecture is capable of handling the creation of corpora of up to at least 100 billion tokens. I also introduce our running demo system which currently serves corpora of up to roughly 20 billion tokens in Dutch, Englisch, French, German, Spanish, and Swedish.},
  Url                      = {http://rolandschaefer.net/?p=749}
}