<i>Pat-in-the-Loop</i>: Declarative Knowledge for Controlling Neural Networks

<i>Pat-in-the-Loop</i>: Declarative Knowledge for Controlling Neural Networks

The dazzling success of neural networks over natural language processing systems is imposing an urgent need to control their behavior with simpler, more direct declarative rules. In this paper, we propose Pat-in-the-Loop as a model to control a specific class of syntax-oriented neural networks by ad...

Full description

Bibliographic Details
Main Authors: Dario Onorati, Pierfrancesco Tommasino, Leonardo Ranaldi, Francesca Fallucchi, Fabio Massimo Zanzotto
Format: Article
Language:English
Published: MDPI AG 2020-12-01
Series:Future Internet
Subjects:
NLP
machine learning
deep learning
AI
human-in-the-loop
Online Access:https://www.mdpi.com/1999-5903/12/12/218

Similar Items

Similar Items