@InProceedings{cabrera-steinert-ross:2017:EACLDemo,
  author    = {Cabrera, Benjamin  and  Steinert, Laura  and  Ross, Bj\"{o}rn},
  title     = {GraWiTas: a Grammar-based Wikipedia Talk Page Parser},
  booktitle = {Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {21--24},
  abstract  = {Wikipedia offers researchers unique insights into the collaboration and
	communication patterns of a large self-regulating community of editors. The
	main medium of direct communication between editors of an article is the
	article’s talk page. However, a talk page file is unstructured and therefore
	difficult to analyse automatically. A few parsers exist that enable its
	transformation into a structured data format. However, they are rarely open
	source, support only a limited subset of the talk page syntax -- resulting in
	the loss of content -- and usually support only one export format. Together
	with this article we offer a very fast, lightweight, open source parser with
	support for various output formats. In a preliminary evaluation it achieved a
	high accuracy. The parser uses a grammar-based approach -- offering a
	transparent implementation and easy extensibility.},
  url       = {http://aclweb.org/anthology/E17-3006}
}