N

Nordic Roberta Wiki

Developed by flax-community
A Nordic RoBERTa model trained on Swedish, Danish, and Norwegian Wikipedia, suitable for fill-mask tasks.
Downloads 13
Release Time : 3/2/2022

Model Overview

This model is a RoBERTa model trained on Swedish, Danish, and Norwegian Wikipedia, primarily used for fill-mask tasks and supports multilingual processing for Nordic languages.

Model Features

Multilingual Support
Supports three Nordic languages: Swedish, Danish, and Norwegian.
Wikipedia-Based Training
Training data sourced from Swedish, Danish, and Norwegian Wikipedia content.
High Performance
Excellent performance in Danish named entity recognition and sentiment analysis tasks.

Model Capabilities

Fill-Mask
Multilingual Text Processing
Named Entity Recognition
Sentiment Analysis

Use Cases

Natural Language Processing
Named Entity Recognition
Used to identify named entities in text, such as person names, locations, etc.
Achieved an average F1 score of 85.75 on the DaNE dataset.
Sentiment Analysis
Used to analyze the sentiment tendency of text.
Achieved an average score of 56.46 in sentiment analysis tasks.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase