Enriching Portuguese Word Embeddings with Visual Information
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 r...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | article |
| Language: | eng |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10174/31872 |
| Country: | Portugal |
| Oai: | oai:dspace.uevora.pt:10174/31872 |
| Summary: | 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. |
|---|