Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering
Lerner, Paul, Ferret, Olivier, Guinaudeau, Camille
–arXiv.org Artificial Intelligence
We present a new pre-training method, Multimodal Inverse Cloze Task, for Knowledge-based Visual Question Answering about named Entities (KVQAE). KVQAE is a recently introduced task that consists in answering questions about named entities grounded in a visual context using a Knowledge Base. Therefore, the interaction between the modalities is paramount to retrieve information and must be captured with complex fusion models. As these models require a lot of training data, we design this pre-training task from existing work in textual Question Answering. It consists in considering a sentence as a pseudo-question and its context as a pseudo-relevant passage and is extended by considering images near texts in multimodal documents. Our method is applicable to different neural network architectures and leads to a 9% relative-MRR and 15% relative-F1 gain for retrieval and reading comprehension, respectively, over a no-pre-training baseline.
arXiv.org Artificial Intelligence
Jan-11-2023
- Country:
- South America > Chile
- Oceania > New Zealand
- South Island > Marlborough District > Blenheim (0.04)
- North America
- Dominican Republic (0.04)
- United States
- Washington > King County
- Seattle (0.04)
- New York > New York County
- New York City (0.05)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Washington > King County
- Europe
- United Kingdom > England
- Greater London > London (0.04)
- Ukraine > Kyiv Oblast
- Kyiv (0.04)
- Romania > Sud - Muntenia Development Region
- Giurgiu County > Giurgiu (0.04)
- Italy > Tuscany
- Florence (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- France > Bourgogne-Franche-Comté
- United Kingdom > England
- Asia > China
- Hong Kong (0.04)
- Genre:
- Research Report > Experimental Study (0.46)
- Industry:
- Government > Regional Government (0.68)
- Technology: