@InProceedings{lai-EtAl:2017:EMNLP2017,
  author    = {Lai, Guokun  and  Xie, Qizhe  and  Liu, Hanxiao  and  Yang, Yiming  and  Hovy, Eduard},
  title     = {RACE: Large-scale ReAding Comprehension Dataset From Examinations},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {785--794},
  abstract  = {We present RACE, a new dataset for benchmark evaluation of methods in the
	reading comprehension task. Collected from the English exams for middle and
	high school Chinese students in the age range between 12 to 18, RACE consists
	of near 28,000 passages and near 100,000 questions generated by human experts
	(English instructors), and covers a variety of topics which are carefully
	designed for evaluating the students' ability in  understanding and reasoning. 
	In particular, the proportion of questions that requires reasoning is much
	larger in RACE than that in other benchmark datasets for reading comprehension,
	and there is a significant gap between the performance of the state-of-the-art
	models (43%) and the ceiling human performance (95%). We hope this new dataset
	can serve as a valuable resource for research and evaluation in machine
	comprehension. The dataset is freely available at
	http://www.cs.cmu.edu/~glai1/data/race/ and the code is available at
	https://github.com/qizhex/RACE\_AR\_baselines.},
  url       = {https://www.aclweb.org/anthology/D17-1082}
}