@InProceedings{lu-EtAl:2016:WLSI-OIAF4HLT2016,
  author    = {Lu, Tingming  and  Zhu, Man  and  Gao, Zhiqiang  and  Gui, Yaocheng},
  title     = {Evaluating Ensemble Based Pre-annotation on Named Entity Corpus Construction in English and Chinese},
  booktitle = {Proceedings of the Third International Workshop on Worldwide Language Service Infrastructure and Second Workshop on Open Infrastructures and Analysis Frameworks for Human Language Technologies (WLSI/OIAF4HLT2016)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {56--60},
  abstract  = {Annotated corpora are crucial language resources, and pre-annotation is an
	usual way to reduce the cost of corpus construction. Ensemble based
	pre-annotation approach combines multiple existing named entity taggers and
	categorizes annotations into normal annotations with high confidence and
	candidate annotations with low confidence, to reduce the human annotation time.
	In this paper, we manually annotate three English datasets under various
	pre-annotation conditions, report the effects of ensemble based pre-annotation,
	and analyze the experimental results. In order to verify the effectiveness of
	ensemble based pre-annotation in other languages, such as Chinese, three
	Chinese datasets are also tested. The experimental results show that the
	ensemble based pre-annotation approach significantly reduces the number of
	annotations which human annotators have to add, and outperforms the baseline
	approaches in reduction of human annotation time without loss in annotation
	performance (in terms of F1-measure), on both English and Chinese datasets.},
  url       = {http://aclweb.org/anthology/W16-5208}
}