papers AI Learner
The Github is limit! Click to go to the new site.

Harnessing Deep Neural Networks with Logic Rules

2019-03-26
Zhiting Hu, Xuezhe Ma, Zhengzhong Liu, Eduard Hovy, Eric Xing

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1603.06318

PDF

http://arxiv.org/pdf/1603.06318


Similar Posts

Comments