Semantic Scholar Open Access 2016 634 sitasi

Harnessing Deep Neural Networks with Logic Rules

Zhiting Hu Xuezhe Ma Zhengzhong Liu E. Hovy E. Xing

Lihat Sumber DOI

Abstrak

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.

Topik & Kata Kunci

Computer Science Mathematics

Penulis (5)

Zhiting Hu

Xuezhe Ma

Zhengzhong Liu

E. Hovy

E. Xing

Format Sitasi

APA MLA BibTeX

Hu, Z., Ma, X., Liu, Z., Hovy, E., Xing, E. (2016). Harnessing Deep Neural Networks with Logic Rules. https://doi.org/10.18653/v1/P16-1228

Akses Cepat

Lihat di Sumber doi.org/10.18653/v1/P16-1228

Informasi Jurnal

Tahun Terbit: 2016
Bahasa: en
Total Sitasi: 634×
Sumber Database: Semantic Scholar
DOI: 10.18653/v1/P16-1228
Akses: Open Access ✓