Welcome to the InfoSci Platform
Reference Hub1
An AI Using Construction Grammar to Understand Text: Parsing Improvements

An AI Using Construction Grammar to Understand Text: Parsing Improvements

Denis Kiselev
Copyright: © 2021 |Volume: 15 |Issue: 2 |Pages: 15
ISSN: 1557-3958|EISSN: 1557-3966|EISBN13: 9781799859833|DOI: 10.4018/IJCINI.20210401.oa4
Cite Article Cite Article

MLA

Kiselev, Denis. "An AI Using Construction Grammar to Understand Text: Parsing Improvements." IJCINI vol.15, no.2 2021: pp.34-48. http://doi.org/10.4018/IJCINI.20210401.oa4

APA

Kiselev, D. (2021). An AI Using Construction Grammar to Understand Text: Parsing Improvements. International Journal of Cognitive Informatics and Natural Intelligence (IJCINI), 15(2), 34-48. http://doi.org/10.4018/IJCINI.20210401.oa4

Chicago

Kiselev, Denis. "An AI Using Construction Grammar to Understand Text: Parsing Improvements," International Journal of Cognitive Informatics and Natural Intelligence (IJCINI) 15, no.2: 34-48. http://doi.org/10.4018/IJCINI.20210401.oa4

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

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.