@InProceedings{boudin-mougard-cram:2016:WNUT,
  author    = {Boudin, Florian  and  Mougard, Hugo  and  Cram, Damien},
  title     = {How Document Pre-processing affects Keyphrase Extraction Performance},
  booktitle = {Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {121--128},
  abstract  = {The SemEval-2010 benchmark dataset has brought renewed attention to the task of
	automatic keyphrase extraction. This dataset is made up of scientific articles
	that were automatically converted from PDF format to plain text and thus
	require careful preprocessing so that irrevelant spans of text do not
	negatively affect keyphrase extraction performance. In previous work, a wide
	range of document preprocessing techniques were described but their impact on
	the overall performance of keyphrase extraction models is still unexplored.
	Here, we re-assess the performance of several keyphrase extraction models and
	measure their robustness against increasingly sophisticated levels of document
	preprocessing.
	Author{2}{Affiliation}},
  url       = {http://aclweb.org/anthology/W16-3917}
}