Please use this identifier to cite or link to this item:
http://hdl.handle.net/10174/31872
|
| Title: | Enriching Portuguese Word Embeddings with Visual Information |
| Authors: | Consoli, Bernardo
Vieira, Renata |
| Keywords: | Word embeddings
Multi-modal |
| Issue Date: | 16-Mar-2022 |
| Publisher: | Springer |
| Citation: | Consoli, B.S., Vieira, R. (2022). Enriching Portuguese Word Embeddings with Visual Information. In: , et al. Computational Processing of the Portuguese Language. PROPOR 2022. Lecture Notes in Computer Science(), vol 13208. Springer, Cham. https://doi.org/10.1007/978-3-030-98305-5_42 |
| 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. |
| URI: | https://rdcu.be/cKEaj
http://hdl.handle.net/10174/31872 |
| ISBN: | 978-3-030-98305-5 |
| Type: | article |
| Appears in Collections: | CIDEHUS - Artigos em Livros de Actas/Proceedings
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
/
CIDEHUS - Centro Interdisciplinar de História, Culturas e Sociedades /
CIDEHUS - Artigos em Livros de Actas/Proceedings /
