Tao Li and Vivek Srikumar
Annual Meeting of the Association for Computational Linguistics (ACL), 2019.


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: ma- chine comprehension, natural language inference, and text chunking. Our experiments show that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes.


Bib Entry

  author = {Li, Tao and Srikumar, Vivek},
  title = {{Augmenting Neural Networks with First-order Logic}},
  booktitle = {Annual Meeting of the Association for Computational Linguistics (ACL)},
  year = {2019}