A Neural Approach for Detecting Morphological Analogies - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

A Neural Approach for Detecting Morphological Analogies

Abstract

Analogical proportions are statements of the form "A is to B as C is to D" that are used for several reasoning and classification tasks in artificial intelligence and natural language processing (NLP). For instance, there are analogy based approaches to semantics as well as to morphology. In fact, symbolic approaches were developed to solve or to detect analogies between character strings, e.g., the axiomatic approach as well as that based on Kolmogorov complexity. In this paper, we propose a deep learning approach to detect morphological analogies, for instance, with reinflexion or conjugation. We present empirical results that show that our framework is competitive with the above-mentioned state of the art symbolic approaches. We also explore empirically its transferability capacity across languages, which highlights interesting similarities between them.
Fichier principal
Vignette du fichier
DSAA2021___NN_for_Morhological_Analogy_Classification___IEEE_Conference_Template.pdf (735.75 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03313556 , version 1 (04-08-2021)

Identifiers

  • HAL Id : hal-03313556 , version 1

Cite

Safa Alsaidi, Amandine Decker, Puthineath Lay, Esteban Marquer, Pierre-Alexandre Murena, et al.. A Neural Approach for Detecting Morphological Analogies. DSAA 2021 - 8th IEEE International Conference on Data Science and Advanced Analytics, Oct 2021, Porto/Online, Portugal. pp.1-10. ⟨hal-03313556⟩
673 View
606 Download

Share

Gmail Facebook X LinkedIn More