N

Ner English Ontonotes

Developed by flair
Flair's built-in English 18-class named entity recognition model, trained on the Ontonotes dataset with an F1 score of 89.27.
Downloads 175.71k
Release Time : 3/2/2022

Model Overview

This is a sequence labeling model based on the LSTM-CRF architecture, designed to recognize 18 types of named entities in English text, including persons, locations, dates, currencies, etc.

Model Features

18-class entity recognition
Capable of recognizing 18 different types of named entities, including persons, locations, dates, currencies, etc.
High precision
Achieves an F1 score of 89.27 on the Ontonotes dataset.
Hybrid word embeddings
Combines GloVe word embeddings with Flair's contextual string embeddings.

Model Capabilities

Text entity recognition
Multi-category entity classification
Sequence labeling

Use Cases

Information extraction
News entity extraction
Extract key information such as persons, locations, and organizations from news texts.
Can accurately identify various named entities in the text.
Financial document processing
Extract monetary amounts, dates, and other information from financial documents.
Can accurately identify currency values and date entities.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase