Brain-Inspired SNN for Deep Learning in Time-Space and Deep Knowledge Representation. NeuCube

2018 ◽  
pp. 201-243
Author(s):  
Nikola K. Kasabov
Keyword(s):  
Deep Learning ◽  
Knowledge Representation ◽  
Deep Knowledge ◽  
Time Space

scholarly journals An AI Using Construction Grammar to Understand Text

2021 ◽  
Vol 15 (2) ◽  
pp. 34-48
Author(s):  
Denis Kiselev
Keyword(s):  
Deep Learning ◽  
Knowledge Representation ◽  
Natural Language ◽  
State Of The Art ◽  
Deep Understanding ◽  
Knowledge Structure ◽  
Construction Grammar ◽  
Anaphora Resolution

This paper describes an AI that uses construction grammar (CG)—a means of knowledge representation for deep understanding of text. The proposed improvements aim at more versatility of the text form and meaning knowledge structure, as well as for intelligent choosing among possible parses. Along with the improvements, computational CG techniques that form the implementation basis are explained. Evaluation experiments utilize a Winograd schema (WS)—a major test for AI—dataset and compare the implementation with state-of-the-art ones. Results have demonstrated that compared with such techniques as deep learning, the proposed CG approach has a higher potential for the task of anaphora resolution involving deep understanding of the natural language.

Sign in / Sign up

Export Citation Format

Share Document