Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering

Open Access
Authors
Publication date 2019
Host editors
  • A. Korhonen
  • D. Traum
  • L. Màrquez
Book title The 57th Annual Meeting of the Association for Computational Linguistics
Book subtitle ACL 2019 : proceedings of the conference : July 28-August 2, 2019, Florence, Italy
ISBN (electronic)
  • 9781950737482
Event The 57th Annual Meeting of the Association for Computational Linguistics - ACL 2019
Pages (from-to) 3601-3605
Publisher Stroudsburg, PA: The Association for Computational Linguistics
Organisations
  • Faculty of Science (FNWI)
  • Interfacultary Research - Institute for Logic, Language and Computation (ILLC)
Abstract
We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which differ by the types of questions involved (Wh-questions and polar questions). We test what impact task difficulty has on continual learning, and whether the order in which a child acquires question types facilitates computational models. Our results show that dramatic forgetting is at play and that task difficulty and order matter. Two well-known current continual learning methods mitigate the problem only to a limiting degree.
Document type Conference contribution
Note With supplemental material
Language English
Published at https://doi.org/10.18653/v1/P19-1350
Other links https://vimeo.com/384787273 http://continual-vista.github.io/
Downloads
P19-1350 (Final published version)
Supplementary materials
Permalink to this page
Back