@InProceedings{nangia-EtAl:2017:RepEval,
  author    = {Nangia, Nikita  and  Williams, Adina  and  Lazaridou, Angeliki  and  Bowman, Samuel},
  title     = {The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations},
  booktitle = {Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1--10},
  abstract  = {This paper presents the results of the RepEval 2017 Shared Task, which
	evaluated neural network sentence representation learning models on the
	Multi-Genre Natural Language Inference corpus (MultiNLI) recently introduced by
	Williams et al. (2017). All of the five participating teams beat the
	bidirectional LSTM (BiLSTM) and continuous bag of words baselines reported in
	Williams et al. The best single model used stacked BiLSTMs with residual
	connections to extract sentence features and reached 74.5% accuracy on the
	genre-matched test set. Surprisingly, the results of the competition were
	fairly consistent across the genre-matched and genre-mismatched test sets, and
	across subsets of the test data representing a variety of linguistic phenomena,
	suggesting that all of the submitted systems learned reasonably
	domain-independent representations for sentence meaning.},
  url       = {http://www.aclweb.org/anthology/W17-5301}
}