@InProceedings{chiarcos_et_al:OASIcs.LDK.2019.7,
  author =	{Chiarcos, Christian and Schenk, Niko},
  title =	{{CoNLL-Merge: Efficient Harmonization of Concurrent Tokenization and Textual Variation}},
  booktitle =	{2nd Conference on Language, Data and Knowledge (LDK 2019)},
  pages =	{7:1--7:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-105-4},
  ISSN =	{2190-6807},
  year =	{2019},
  volume =	{70},
  editor =	{Eskevich, Maria and de Melo, Gerard and F\"{a}th, Christian and McCrae, John P. and Buitelaar, Paul and Chiarcos, Christian and Klimek, Bettina and Dojchinovski, Milan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.LDK.2019.7},
  URN =		{urn:nbn:de:0030-drops-103717},
  doi =		{10.4230/OASIcs.LDK.2019.7},
  annote =	{Keywords: data heterogeneity, tokenization, tab-separated values (TSV) format, linguistic annotation, merging}
}