Author(s): Consoli, Bernardo ; Vieira, Renata
Date: 2022
Persistent ID: http://hdl.handle.net/10174/31872
Origin: Repositório Científico da Universidade de Évora
Subject(s): Word embeddings; Multi-modal
Document details
Enriching Portuguese Word Embeddings with Visual Information
Description
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.
FCT CEECIND/01997/2017, UIDB/00057/2020
Document Type
Journal article
Language English
Language English
