@InProceedings{poliak-EtAl:2018:BlackboxNLP,
  author    = {Poliak, Adam  and  Haldar, Aparajita  and  Rudinger, Rachel  and  Hu, J. Edward  and  Pavlick, Ellie  and  White, Aaron Steven  and  Van Durme, Benjamin},
  title     = {Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation},
  booktitle = {Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP},
  month     = {November},
  year      = {2018},
  address   = {Brussels, Belgium},
  publisher = {Association for Computational Linguistics},
  pages     = {337--340},
  abstract  = {We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation encoded by a neural network captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. Our collection of diverse datasets is available at http://www.decomp.net/ and will grow over time as additional resources are recast and added from novel sources.},
  url       = {http://www.aclweb.org/anthology/W18-5441}
}