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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics |
Place of Publication | Florence |
Publisher | Association for Computational Linguistics |
Publication date | Jul 2019 |
Pages | 3601–3605 |
ISBN (Electronic) | 978-1-950737-48-2 |
Publication status | Published - Jul 2019 |
Keywords
- Catastrophic Forgetting
- Visual Question Answering
- Continual Learning
- Task Difficulty
- Question Types