ITU

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

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

View graph of relations

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 languageEnglish
Title of host publicationProceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Place of PublicationFlorence
PublisherAssociation for Computational Linguistics
Publication dateJul 2019
Pages3601–3605
ISBN (Electronic)978-1-950737-48-2
Publication statusPublished - Jul 2019

Downloads

No data available

ID: 84271576