Harnessing Deep Neural Networks with Logic Rules

Code

• github.com/ZhitingHu/logicnn
  none★ 0
• github.com/martiansideofthemoon/logic-rules-sentiment
  tf★ 0

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.

Tasks

Benchmark Results

Reproductions