Compositionality as an Analogical Process: Introducing ANNE - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Proceedings of the Workshop on Cognitive Aspects of the Lexicon Année : 2022

Compositionality as an Analogical Process: Introducing ANNE

Emmanuele Chersoni
Philippe Blache

Résumé

Usage-based constructionist approaches consider language a structured inventory of constructions, form-meaning pairings of different schematicity and complexity, and claim that the more a linguistic pattern is encountered, the more it becomes accessible to speakers. However, when an expression is unavailable, what processes underlie the interpretation? While traditional answers rely on the principle of compositionality, for which the meaning is built word-byword and incrementally, usage-based theories argue that novel utterances are created based on previously experienced ones through analogy, mapping an existing structural pattern onto a novel instance. Starting from this theoretical perspective, we propose here a computational implementation of these assumptions. As the principle of compositionality has been used to generate distributional representations of phrases, we propose a neural network simulating the construction of phrasal embedding as an analogical process. Our framework, inspired by word2vec and computer vision techniques, was evaluated on tasks of generalization from existing vectors.
Fichier principal
Vignette du fichier
2022.cogalex-1.10.pdf (3.43 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04052104 , version 1 (30-03-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04052104 , version 1

Citer

Giulia Rambelli, Emmanuele Chersoni, Philippe Blache, Lenci Alessandro. Compositionality as an Analogical Process: Introducing ANNE. Workshop on Cognitive Aspects of the Lexicon, Proceedings of the Workshop on Cognitive Aspects of the Lexicon , pp.78-96, 2022, 978-1-959429-01-2. ⟨hal-04052104⟩
37 Consultations
34 Téléchargements

Partager

Gmail Facebook X LinkedIn More