%0 Conference Proceedings %T Cooperative Learning of Disjoint Syntax and Semantics %A Havrylov, Serhii %A Kruszewski, Germán %A Joulin, Armand %Y Burstein, Jill %Y Doran, Christy %Y Solorio, Thamar %S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) %D 2019 %8 June %I Association for Computational Linguistics %C Minneapolis, Minnesota %F havrylov-etal-2019-cooperative %X There has been considerable attention devoted to models that learn to jointly infer an expression’s syntactic structure and its semantics. Yet, Nangia and Bowman (2018) has recently shown that the current best systems fail to learn the correct parsing strategy on mathematical expressions generated from a simple context-free grammar. In this work, we present a recursive model inspired by Choi et al. (2018) that reaches near perfect accuracy on this task. Our model is composed of two separated modules for syntax and semantics. They are cooperatively trained with standard continuous and discrete optimisation schemes. Our model does not require any linguistic structure for supervision, and its recursive nature allows for out-of-domain generalisation. Additionally, our approach performs competitively on several natural language tasks, such as Natural Language Inference and Sentiment Analysis. %R 10.18653/v1/N19-1115 %U https://aclanthology.org/N19-1115 %U https://doi.org/10.18653/v1/N19-1115 %P 1118-1128