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.

Date

January 1, 1970

Authors

Zhiting Hu, Xuezhe Ma, Zhengzhong Liu, Eduard Hovy, Eric Xing

Conference

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016)

Volume

1

Publisher

Association for Computational Linguistics