@INPROCEEDINGS{GRQB14,
AUTHOR = {Dirk Goldhahn, Steffen Remus, Uwe Quasthoff and Chris Biemann},
TITLE = {Top-Level Domain Crawling for Producing Comprehensive Monolingual Corpora from the Web},
BOOKTITLE = {Workshop on Challenges in the Management of Large Corpora (CMLC-2), LREC, Reykjavík},
YEAR = {2014}
}