Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering - Laboratoire Interdisciplinaire des Sciences du Numérique Access content directly
Preprints, Working Papers, ... Year :

Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering

Abstract

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.
Fichier principal
Vignette du fichier
main.pdf (5.47 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
licence : CC BY - Attribution

Dates and versions

hal-03933089 , version 1 (10-01-2023)

Licence

Attribution

Identifiers

  • HAL Id : hal-03933089 , version 1

Cite

Paul Lerner, Olivier Ferret, Camille Guinaudeau. Multimodal Inverse Cloze Task for Knowledge-based Visual Question Answering. 2023. ⟨hal-03933089⟩
58 View
12 Download

Share

Gmail Facebook Twitter LinkedIn More