%0 Conference Proceedings %T Hypothesis Only Baselines in Natural Language Inference %A Poliak, Adam %A Naradowsky, Jason %A Haldar, Aparajita %A Rudinger, Rachel %A Van Durme, Benjamin %Y Nissim, Malvina %Y Berant, Jonathan %Y Lenci, Alessandro %S Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics %D 2018 %8 June %I Association for Computational Linguistics %C New Orleans, Louisiana %F poliak-etal-2018-hypothesis %X We propose a hypothesis only baseline for diagnosing Natural Language Inference (NLI). Especially when an NLI dataset assumes inference is occurring based purely on the relationship between a context and a hypothesis, it follows that assessing entailment relations while ignoring the provided context is a degenerate solution. Yet, through experiments on 10 distinct NLI datasets, we find that this approach, which we refer to as a hypothesis-only model, is able to significantly outperform a majority-class baseline across a number of NLI datasets. Our analysis suggests that statistical irregularities may allow a model to perform NLI in some datasets beyond what should be achievable without access to the context. %R 10.18653/v1/S18-2023 %U https://aclanthology.org/S18-2023 %U https://doi.org/10.18653/v1/S18-2023 %P 180-191