@InProceedings{chambers:2017:LSDSem,
  author    = {Chambers, Nathanael},
  title     = {Behind the Scenes of an Evolving Event Cloze Test},
  booktitle = {Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {41--45},
  abstract  = {This paper analyzes the narrative event cloze test and its recent evolution.
	The test removes one event from a document's chain of events, and systems
	predict the missing event.
	Originally proposed to evaluate learned knowledge of event scenarios (e.g.,
	scripts and frames), most recent work now builds ngram-like language models
	(LM) to beat the test.
	This paper argues that the test has slowly/unknowingly been altered to
	accommodate LMs.5
	Most notably, tests are auto-generated rather than by hand, and no effort is
	taken to include core script events.
	Recent work is not clear on evaluation goals and contains contradictory
	results.
	We implement several models, and show that the test's bias to high-frequency
	events explains the inconsistencies.
	We conclude with recommendations on how to return to the test's original
	intent, and offer brief suggestions on a path forward.},
  url       = {http://aclweb.org/anthology/W17-0905}
}