Exécution de notre outil de synthèse sur un nouvel article
Vérifiez l’article ci-dessous, puis lancez sa synthèse.
Harnessing Deep Neural Networks with Logic Rules
Zhiting Hu (Carnegie Mellon University), Xuezhe Ma (Carnegie Mellon University), Zhengzhong Liu (Carnegie Mellon University), Eduard H. Hovy (Carnegie Mellon University), Eric P. Xing (Carnegie Mellon University)
Résumé : 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.