N

Ner Dutch Large

Developed by flair
Flair's built-in Dutch 4-category named entity recognition large model, based on XLM-R embeddings and FLERT technology, achieves an F1 score of 95.25 on the CoNLL-03 Dutch dataset.
Downloads 147.32k
Release Time : 3/2/2022

Model Overview

This model is used for named entity recognition in Dutch texts, capable of identifying four categories of entities: persons, locations, organizations, and other names.

Model Features

Document-level context understanding
Uses FLERT technology to leverage document-level contextual information for improved entity recognition accuracy.
Multi-category entity recognition
Capable of simultaneously identifying four categories of entities: persons (PER), locations (LOC), organizations (ORG), and others (MISC).
High performance
Achieves an F1 score of 95.25 on the standard CoNLL-03 Dutch dataset.

Model Capabilities

Dutch text processing
Named entity recognition
Sequence labeling

Use Cases

Text analysis
News text entity extraction
Automatically identifies names of persons, locations, and organizations from Dutch news articles.
Accurately tags various named entities.
Document information extraction
Processes entity information in legal or business documents.
Assists in document classification and information retrieval.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase