%0 Conference Proceedings %T Augmenting Neural Networks with First-order Logic %A Li, Tao %A Srikumar, Vivek %Y Korhonen, Anna %Y Traum, David %Y Màrquez, Lluís %S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics %D 2019 %8 July %I Association for Computational Linguistics %C Florence, Italy %F li-srikumar-2019-augmenting %X Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this paper, we present a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction. Our framework systematically compiles logical statements into computation graphs that augment a neural network without extra learnable parameters or manual redesign. We evaluate our modeling strategy on three tasks: machine comprehension, natural language inference, and text chunking. Our experiments show that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes. %R 10.18653/v1/P19-1028 %U https://aclanthology.org/P19-1028 %U https://doi.org/10.18653/v1/P19-1028 %P 292-302