S

Span Marker Mbert Base Multinerd

Developed by tomaarsen
This is a multilingual named entity recognition model trained on the MultiNERD dataset, supporting over 20 languages, using bert-base-multilingual-cased as the underlying encoder.
Downloads 5,591
Release Time : 8/7/2023

Model Overview

This model is used for multilingual named entity recognition tasks, capable of identifying various entity types such as persons, organizations, locations, etc. in text.

Model Features

Multilingual Support
Supports named entity recognition in over 20 languages
High Accuracy
Achieves an F1 score of 0.92478 on the MultiNERD test set
Broad Entity Type Coverage
Can identify 18 different types of entities, including persons, organizations, locations, animals, diseases, etc.

Model Capabilities

Multilingual text analysis
Named entity recognition
Entity classification

Use Cases

Text Analysis
Multilingual News Analysis
Extract key entities from multilingual news texts
Accurately identifies entities such as persons, organizations, and locations in texts of different languages
Cross-language Information Extraction
Extract structured information from multilingual documents
Supports entity recognition in over 20 languages, facilitating cross-language information integration
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase