AIbase
EN
Home
Bert Base Swedish Cased Reallysimple Ner
B

Bert Base Swedish Cased Reallysimple Ner

Developed by KBLab
Swedish NER model based on KB-BERT architecture, fine-tuned on SUCX 3.0 NER corpus while preserving original case features
Sequence Labeling
Transformers
 Other#Swedish NER#Case-preserving#Non-BIO tagging
Downloads 55
Release Time : 3/2/2022

Model Overview

This model is specifically designed for named entity recognition tasks in Swedish texts, employing a simple tagging scheme for case-sensitive text data

Model Features

Case-sensitive processing
The model preserves original text case features, suitable for case-sensitive named entity recognition scenarios
Simplified tagging scheme
Uses non-BIO encoding system without distinguishing between beginning (B) and inside (I) entity markers, simplifying the annotation process
Swedish language optimization
Fine-tuned based on Swedish pre-trained models, specifically optimized for Swedish text characteristics

Model Capabilities

Swedish text processing
Named entity recognition
Sequence labeling

Use Cases

Text information extraction
Geographical name recognition
Identifying place name entities in Swedish texts (e.g., 'Lönneberga' in the example)
Accurately recognizes geographical names in Swedish texts
Person name recognition
Extracting personal name entities from texts (e.g., 'Emil' in the example)
Effectively identifies Swedish personal names and their variant forms
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase