Psycholinguistics meets Continual Learning: Measuring Catastrophic Forgetting in Visual Question Answering
- Claudio Greco,
- ,
- Raquel Fernandez,
- Raffaella Bernardi
- University of Trento,
- ,
- University of Amsterdam
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOpen access
Publication Information
Output type
Research Output:
Conference Article in Proceeding or Book/Report chapter
Article in proceedings
Peer-reviewOriginal language
EnglishPages from-to (Number of pages)
Pages 3601–3605Publication milestones
- Published - 07/2019
Publication status
Published - 07/2019
Place of publication
FlorencePublisher
Association for Computational Linguistics, United StatesISBN (Electronic)
978-1-950737-48-2Host publication title
Proceedings of the 57th Annual Meeting of the Association for Computational LinguisticsAbstract
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.
Access to documents
Accepted author manuscript, 477.06 KB
Accepted author manuscript
