@InProceedings{derczynski-bontcheva-roberts:2016:COLING,
  author    = {Derczynski, Leon  and  Bontcheva, Kalina  and  Roberts, Ian},
  title     = {Broad Twitter Corpus: A Diverse Named Entity Recognition Resource},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1169--1179},
  abstract  = {One of the main obstacles, hampering method development and comparative
	evaluation of named entity recognition in social media, is the lack of a
	sizeable, diverse, high quality annotated corpus, analogous to the CoNLL'2003
	news dataset. For instance, the biggest Ritter tweet corpus is only 45,000
	tokens -- a mere 15% the size of CoNLL'2003. Another major shortcoming is the
	lack of temporal, geographic, and author diversity. This paper introduces the
	Broad Twitter Corpus (BTC), which is not only significantly bigger, but sampled
	across different regions, temporal periods, and types of Twitter users. The
	gold-standard named entity annotations are made by a combination of NLP experts
	and crowd workers, which enables us to harness crowd recall while maintaining
	high quality. We also measure the entity drift observed in our dataset (i.e.
	how entity representation varies over time), and compare to newswire.  The
	corpus is released openly, including source text and intermediate annotations.},
  url       = {http://aclweb.org/anthology/C16-1111}
}