@InProceedings{barbaresi:2016:WAC-X,
  author    = {Barbaresi, Adrien},
  title     = {Efficient construction of metadata-enhanced web corpora},
  booktitle = {Proceedings of the 10th Web as Corpus Workshop},
  month     = {August},
  year      = {2016},
  address   = {Berlin},
  publisher = {Association for Computational Linguistics},
  pages     = {7--16},
  url       = {http://anthology.aclweb.org/W16-2602}
}