Learning English with Peppa Pig - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Transactions of the Association for Computational Linguistics Année : 2022

Learning English with Peppa Pig

Résumé

Recent computational models of the acquisition of spoken language via grounding in perception exploit associations between spoken and visual modalities and learn to represent speech and visual data in a joint vector space. A major unresolved issue from the point of ecological validity is the training data, typically consisting of images or videos paired with spoken descriptions of what is depicted. Such a setup guarantees an unrealistically strong correlation between speech and the visual data. In the real world the coupling between the linguistic and the visual modality is loose, and often confounded by correlations with non-semantic aspects of the speech signal. Here we address this shortcoming by using a dataset based on the children's cartoon Peppa Pig. We train a simple bi-modal architecture on the portion of the data consisting of dialog between characters, and evaluate on segments containing descriptive narrations. Despite the weak and confounded signal in this training data, our model succeeds at learning aspects of the visual semantics of spoken language.
Fichier principal
Vignette du fichier
tacl_a_00498.pdf (567.44 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03775969 , version 1 (13-09-2022)

Licence

Paternité

Identifiants

  • HAL Id : hal-03775969 , version 1

Citer

Mitja Nikolaus, Afra Alishahi, Grzegorz Chrupała. Learning English with Peppa Pig. Transactions of the Association for Computational Linguistics, 2022, 10. ⟨hal-03775969⟩
68 Consultations
75 Téléchargements

Partager

Gmail Facebook X LinkedIn More