@InProceedings{tack-EtAl:2017:BEA,
  author    = {Tack, Ana\"{i}s  and  Fran\c{c}ois, Thomas  and  Roekhaut, Sophie  and  Fairon, C\'{e}drick},
  title     = {Human and Automated CEFR-based Grading of Short Answers},
  booktitle = {Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {169--179},
  abstract  = {This paper is concerned with the task of automatically assessing the written
	proficiency level of non-native (L2) learners of English.
	Drawing on previous research on automated L2 writing assessment following the
	Common European Framework of Reference for Languages (CEFR), we investigate the
	possibilities and difficulties of deriving the CEFR level from short answers to
	open-ended questions, which has not yet been subjected to numerous studies up
	to date.
	The object of our study is twofold: to examine the intricacy involved with both
	human and automated CEFR-based grading of short answers.
	On the one hand, we describe the compilation of a learner corpus of short
	answers graded with CEFR levels by three certified Cambridge examiners.
	We mainly observe that, although the shortness of the answers is reported as
	undermining a clear-cut evaluation, the length of the answer does not
	necessarily correlate with inter-examiner disagreement.
	On the other hand, we explore the development of a soft-voting system for the
	automated CEFR-based grading of short answers and draw tentative conclusions
	about its use in a computer-assisted testing (CAT) setting.},
  url       = {http://www.aclweb.org/anthology/W17-5018}
}