Solving analogies on words based on minimal complexity transformation

Pierre Alexandre Murena*, Marie Al-Ghossein, Jean Louis Dessalles, Antoine Cornuéjols

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

34 Downloads (Pure)

Abstract

Analogies are 4-ary relations of the form “A is to B as C is to D”. When A, B and C are fixed, we call analogical equation the problem of finding the correct D. A direct applicative domain is Natural Language Processing, in which it has been shown successful on word inflections, such as conjugation or declension. If most approaches rely on the axioms of proportional analogy to solve these equations, these axioms are known to have limitations, in particular in the nature of the considered flections. In this paper, we propose an alternative approach, based on the assumption that optimal word inflections are transformations of minimal complexity. We propose a rough estimation of complexity for word analogies and an algorithm to find the optimal transformations. We illustrate our method on a large-scale benchmark dataset and compare with state-of-the-art approaches to demonstrate the interest of using complexity to solve analogies on words.

Original languageEnglish
Title of host publicationProceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
EditorsChristian Bessiere
Pages1848-1854
Number of pages7
ISBN (Electronic)9780999241165
DOIs
Publication statusPublished - 2020
MoE publication typeA4 Article in a conference publication
EventInternational Joint Conference on Artificial Intelligence - Yokohama, Japan
Duration: 7 Jan 202115 Jan 2021
Conference number: 29

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
PublisherIJCAI
Volume2021-January
ISSN (Print)1045-0823

Conference

ConferenceInternational Joint Conference on Artificial Intelligence
Abbreviated titleIJCAI
CountryJapan
CityYokohama
Period07/01/202115/01/2021

Cite this