Learning to Reason with Third Order Tensor Products

Part of Advances in Neural Information Processing Systems 31 (NeurIPS 2018)

Bibtex »Metadata »Paper »Reviews »Supplemental »

Authors

Imanol Schlag, Jürgen Schmidhuber

Abstract

<p>We combine Recurrent Neural Networks with Tensor Product Representations to learn combinatorial representations of sequential data. This improves symbolic interpretation and systematic generalisation. Our architecture is trained end-to-end through gradient descent on a variety of simple natural language reasoning tasks, significantly outperforming the latest state-of-the-art models in single-task and all-tasks settings. We also augment a subset of the data such that training and test data exhibit large systematic differences and show that our approach generalises better than the previous state-of-the-art.</p>