Enriching Portuguese Word Embeddings with Visual Information

Abstract

This work focuses on the enrichment of existing Portuguese word embeddings with visual information. The combined text-image embeddings were tested against their text-only counterparts in common NLP tasks. The new embeddings were tested in two different domains - general news and a geosciences. The results show an increase in perfor- mance for several tasks, which indicates that visual information fusion for word embeddings can be useful for certain tasks.