Pat-in-the-Loop: Declarative Knowledge for Controlling Neural Networks

Dario Onorati, Pierfrancesco Tommasino, Leonardo Ranaldi, Francesca Fallucchi and Fabio Massimo Zanzotto
Additional contact information
Dario Onorati: Department of Enterprise Engineering, University of Rome Tor Vergata, 00133 Roma, Italy
Pierfrancesco Tommasino: Department of Enterprise Engineering, University of Rome Tor Vergata, 00133 Roma, Italy
Leonardo Ranaldi: Department of Innovation and Information Engineering, Guglielmo Marconi University, 00193 Roma, Italy
Francesca Fallucchi: Department of Innovation and Information Engineering, Guglielmo Marconi University, 00193 Roma, Italy
Fabio Massimo Zanzotto: Department of Enterprise Engineering, University of Rome Tor Vergata, 00133 Roma, Italy

Future Internet, 2020, vol. 12, issue 12, 1-12

Abstract: 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 adding declarative rules. In Pat-in-the-Loop, distributed tree encoders allow to exploit parse trees in neural networks, heat parse trees visualize activation of parse trees, and parse subtrees are used as declarative rules in the neural network. Hence, Pat-in-the-Loop is a model to include human control in specific natural language processing (NLP)-neural network (NN) systems that exploit syntactic information, which we will generically call Pat. A pilot study on question classification showed that declarative rules representing human knowledge, injected by Pat, can be effectively used in these neural networks to ensure correctness, relevance, and cost-effective.

Keywords: NLP; machine learning; deep learning; AI; human-in-the-loop (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/12/12/218/pdf (application/pdf)
https://www.mdpi.com/1999-5903/12/12/218/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:12:y:2020:i:12:p:218-:d:454952

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().