Communication Dans Un Congrès Année : 2022

A Deep Learning Approach to Solving Morphological Analogies

Résumé

Analogical proportions are statements of the form "A is to B as C is to D". They support analogical inference and provide a logical framework to address learning, transfer, and explainability concerns. This logical framework finds useful applications in AI and natural language processing (NLP). In this paper, we address the problem of solving morphological analogies using a retrieval approach named ANNr. Our deep learning framework encodes structural properties of analogical proportions and relies on a specifically designed embedding model capturing morphological characteristics of words. We demonstrate that ANNr outperforms the state of the art on 11 languages. We analyze ANNr results for Navajo and Georgian, languages on which the model performs worst and best, to explore potential correlations between the mistakes of ANNr and linguistic properties.

Fichier principal
Vignette du fichier
ICCBR___Analogy_Solving_by_Retrieval_in_Morphology___LNCS.pdf (1 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Recherche Data Gouv

Cite 10.12763/MLCFIE Logiciel Marquer, Esteban; Couceiro, Miguel; Safa Alsaidi; Amandine Decker, 2022, "Siganalogies - morphological analogies from Sigmorphon 2016 and 2019", https://doi.org/10.12763/MLCFIE, Recherche Data Gouv, V1

Dates et versions

hal-03660625 , version 1 (06-05-2022)

Licence

Identifiants

Citer

Esteban Marquer, Safa Alsaidi, Amandine Decker, Pierre-Alexandre Murena, Miguel Couceiro. A Deep Learning Approach to Solving Morphological Analogies. 30th International Conference on Case-Based Reasoning (ICCBR2022), Sep 2022, Nancy, France. pp.159--174, ⟨10.1007/978-3-031-14923-8_11⟩. ⟨hal-03660625⟩
807 Consultations
1050 Téléchargements

Altmetric

Partager

  • More