VisualSem: A High-quality Knowledge Graph for Vision and Language

TL;DR

VisualSem is a high-quality, multilingual knowledge graph with images and relations designed to enhance vision-language models, along with a retrieval model for effective integration into neural pipelines.

Contribution

We introduce VisualSem, a comprehensive knowledge graph with visual and multilingual data, and a neural multi-modal retrieval model for improved vision-language understanding.

Findings

VisualSem covers diverse domains with high-quality data.

The retrieval model effectively links images and sentences to KG entities.

VisualSem and the retrieval model are publicly available for research use.

Abstract

An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge repositories. However, many existing knowledge bases only cover limited domains, or suffer from noisy data, and most of all are typically hard to integrate into neural language pipelines. To fill this gap, we release VisualSem: a high-quality knowledge graph (KG) which includes nodes with multilingual glosses, multiple illustrative images, and visually relevant relations. We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG. This multi-modal retrieval model can be integrated into any (neural network) model pipeline. We encourage the research community to use VisualSem for data augmentation and/or as a source of grounding, among other possible uses. VisualSem as well as the multi-modal retrieval models are publicly available and can be downloaded in this URL: https://github.com/iacercalixto/visualsem