@InProceedings{joshi-EtAl:2017:Long,
  author    = {Joshi, Mandar  and  Choi, Eunsol  and  Weld, Daniel  and  Zettlemoyer, Luke},
  title     = {TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {1601--1611},
  abstract  = {We present TriviaQA, a challenging reading comprehension dataset containing
	over 650K question-answer-evidence triples. TriviaQA includes 95K
	question-answer  pairs authored by trivia enthusiasts and independently
	gathered evidence documents, six per question on average, that provide high
	quality distant supervision for answering the questions. We show that, in
	comparison to other recently introduced large-scale datasets, TriviaQA (1) has
	relatively complex, compositional questions,  (2)  has considerable 
	syntactic and  lexical                                      variability  between     
	     
	questions and 
	corresponding 
	answer-evidence  sentences,  and  (3) requires more cross sentence reasoning to
	find answers.  We also present two baseline algorithms: a feature-based
	classifier and a state-of-the-art neural network, that performs well on SQuAD
	reading comprehension. Neither approach comes close to human performance (23%
	and 40% vs. 80%), suggesting that TriviaQA is a challenging testbed that is
	worth significant future study.},
  url       = {http://aclweb.org/anthology/P17-1147}
}