“…NLI (Dagan et al, 2005;Iftene and Balahur-Dobrescu, 2007;MacCartney and Manning, 2008;MacCartney and Manning, 2009;MacCartney, 2009;Angeli and Manning, 2014;Bowman et al, 2015), also known as recognizing textual entailment (RTE), aims to model the logical relationships between two sentences, e.g., as a binary (entailment vs. non-entailment) or three-way classification (entailment, contradiction, and neutral). Recently deep learning algorithms have been proposed (Bowman et al, 2015;Chen et al, 2017a;Chen et al, 2017b;Chen et al, 2017c;Chen et al, 2018;Peters et al, 2018;Yoon et al, 2018;Kiela et al, 2018;Talman et al, 2018;Yang et al, 2019;Devlin et al, 2019). In this paper we will describe and evaluate our neural natural logic models on NLI.…”