@inproceedings{3060161ff6d048b8881ab870c0bf2089,
title = "Annotation artifacts in natural language inference data",
abstract = "Large-scale datasets for natural language inference are created by presenting crowd workers with a sentence (premise), and asking them to generate three new sentences (hypotheses) that it entails, contradicts, or is logically neutral with respect to. We show that, in a significant portion of such data, this protocol leaves clues that make it possible to identify the label by looking only at the hypothesis, without observing the premise. Specifically, we show that a simple text categorization model can correctly classify the hypothesis alone in about 67% of SNLI (Bowman et al., 2015) and 53% of MultiNLI (Williams et al., 2018). Our analysis reveals that specific linguistic phenomena such as negation and vagueness are highly correlated with certain inference classes. Our findings suggest that the success of natural language inference models to date has been overestimated, and that the task remains a hard open problem.",
author = "Suchin Gururangan and Swabha Swayamdipta and Omer Levy and Roy Schwartz and Bowman, {Samuel R.} and Smith, {Noah A.}",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics.; 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",
year = "2018",
language = "الإنجليزيّة",
series = "NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "107--112",
booktitle = "Short Papers",
address = "الولايات المتّحدة",
}