Harnessing Deep Neural Networks with Logic Rules
Machine Learning
2020-08-11 v6 Artificial Intelligence
Computation and Language
Machine Learning
Abstract
Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop an iterative distillation method that transfers the structured information of logic rules into the weights of neural networks. We deploy the framework on a CNN for sentiment analysis, and an RNN for named entity recognition. With a few highly intuitive rules, we obtain substantial improvements and achieve state-of-the-art or comparable results to previous best-performing systems.
Cite
@article{arxiv.1603.06318,
title = {Harnessing Deep Neural Networks with Logic Rules},
author = {Zhiting Hu and Xuezhe Ma and Zhengzhong Liu and Eduard Hovy and Eric Xing},
journal= {arXiv preprint arXiv:1603.06318},
year = {2020}
}
Comments
Fix typos in appendix. ACL 2016