Abstract
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.- Anthology ID:
- 2022.tacl-1.54
- Volume:
- Transactions of the Association for Computational Linguistics, Volume 10
- Month:
- Year:
- 2022
- Address:
- Cambridge, MA
- Editors:
- Brian Roark, Ani Nenkova
- Venue:
- TACL
- SIG:
- Publisher:
- MIT Press
- Note:
- Pages:
- 922–936
- Language:
- URL:
- https://aclanthology.org/2022.tacl-1.54
- DOI:
- 10.1162/tacl_a_00498
- Cite (ACL):
- Mitja Nikolaus, Afra Alishahi, and Grzegorz Chrupała. 2022. Learning English with Peppa Pig. Transactions of the Association for Computational Linguistics, 10:922–936.
- Cite (Informal):
- Learning English with Peppa Pig (Nikolaus et al., TACL 2022)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2022.tacl-1.54.pdf