Solving analogies on words based on minimal complexity transformation

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

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

45 Lataukset (Pure)

Abstrakti

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.

AlkuperäiskieliEnglanti
OtsikkoProceedings of the 29th International Joint Conference on Artificial Intelligence, IJCAI 2020
ToimittajatChristian Bessiere
Sivut1848-1854
Sivumäärä7
ISBN (elektroninen)9780999241165
DOI - pysyväislinkit
TilaJulkaistu - 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaInternational Joint Conference on Artificial Intelligence - Yokohama, Japani
Kesto: 7 tammikuuta 202115 tammikuuta 2021
Konferenssinumero: 29

Julkaisusarja

NimiIJCAI International Joint Conference on Artificial Intelligence
KustantajaIJCAI
Vuosikerta2021-January
ISSN (painettu)1045-0823

Conference

ConferenceInternational Joint Conference on Artificial Intelligence
LyhennettäIJCAI
MaaJapani
KaupunkiYokohama
Ajanjakso07/01/202115/01/2021

Siteeraa tätä