distilroberta-base-ner-wikiann-conll2003-4-class Open Source Model - A Named Entity Recognition Tool Supporting 4-Class Entity Recognition

Distilroberta Base Ner Wikiann Conll2003 4 Class

Developed by philschmid

A named entity recognition model based on DistilRoBERTa-base, fine-tuned on the wikiann and conll2003 datasets, supporting 4-class entity recognition.

Sequence Labeling

Transformers

Open Source License:Apache-2.0 #High-precision NER #Multilingual entity recognition #Lightweight RoBERTa

Downloads 16

Release Time : 3/2/2022

Model Overview

This model is designed for Named Entity Recognition (NER) tasks, capable of identifying person names (PER), organization names (ORG), location names (LOC), and miscellaneous entities (MISC) in text.

Model Features

High-precision entity recognition

Achieves an F1 score of 95.39 on the combined dataset, demonstrating excellent performance.

Multi-category support

Supports recognition of 4 entity types: person names (PER), organization names (ORG), location names (LOC), and miscellaneous entities (MISC).

Efficient model

Based on DistilRoBERTa-base, it reduces model size while maintaining performance.

Model Capabilities

Text entity recognition

Multi-category entity classification

Use Cases

Information extraction

News text analysis

Extract key information such as person names, organization names, and location names from news articles.

Can accurately identify over 90% of entities

Document processing

Automatically process and analyze named entities in documents.

🚀 distilroberta-base-ner-wikiann-conll2003-4-class

This model is a fine - tuned version of distilroberta-base on the wikiann and conll2003 dataset, which can be used for token classification tasks.

🚀 Quick Start

This model is a fine - tuned version of distilroberta-base on the wikiann and conll2003 dataset. It consists of the classes of conll2003: O (0), B - PER (1), I - PER (2), B - ORG (3), I - ORG (4), B - LOC (5), I - LOC (6), B - MISC (7), I - MISC (8).

Eval F1 - Score: 95.39 (merged dataset)
Test F1 - Score: 90.75 (merged dataset)

✨ Features

Token Classification: Suitable for token - classification tasks.
Fine - Tuned: Based on the distilroberta - base model, fine - tuned on the wikiann and conll2003 dataset.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline

tokenizer = AutoTokenizer.from_pretrained("philschmid/distilroberta-base-ner-wikiann-conll2003-4-class")
model = AutoModelForTokenClassification.from_pretrained("philschmid/distilroberta-base-ner-wikiann-conll2003-4-class")

nlp = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
example = "My name is Philipp and live in Germany"

nlp(example)

📚 Documentation

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 4.9086903597787154e - 05
train_batch_size: 32
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9, 0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 5.0
mixed_precision_training: Native AMP

Training results

It achieves the following results on the evaluation set:

Loss: 0.0705
Precision: 0.9492
Recall: 0.9585
F1: 0.9539
Accuracy: 0.9882

It achieves the following results on the test set:

Loss: 0.239
Precision: 0.8984
Recall: 0.9168
F1: 0.9075
Accuracy: 0.9741

Framework versions

Transformers 4.6.1
Pytorch 1.8.1+cu101
Datasets 1.6.2
Tokenizers 0.10.2

📄 License

This model is licensed under the Apache - 2.0 license.

Property	Details
Model Type	distilroberta-base-ner-wikiann-conll2003-4-class
Training Data	wikiann - conll2003
Metrics	Precision, Recall, F1, Accuracy

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご