@InProceedings{vanschijndel-schuler:2016:CL4LC,
  author    = {van Schijndel, Marten  and  Schuler, William},
  title     = {Addressing surprisal deficiencies in reading time models},
  booktitle = {Proceedings of the Workshop on Computational Linguistics for Linguistic Complexity (CL4LC)},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {32--37},
  abstract  = {This study demonstrates a weakness in how n-gram and PCFG surprisal are used to
	predict reading times in eye-tracking data. In particular, the information
	conveyed by words skipped during saccades is not usually included in the
	surprisal measures. This study shows that correcting the surprisal calculation
	improves n-gram surprisal and that upcoming n-grams affect reading times,
	replicating previous findings of how lexical frequencies affect reading times.
	In contrast, the predictivity of PCFG surprisal does not benefit from the
	surprisal correction despite the fact that lexical sequences skipped by
	saccades are processed by readers, as demonstrated by the corrected n-gram
	measure. These results raise questions about the formulation of
	information-theoretic measures of syntactic processing such as PCFG surprisal
	and entropy reduction when applied to reading times.},
  url       = {http://aclweb.org/anthology/W16-4104}
}