xlm-roberta-base-finetuned-panx-all Open-source Model - Supports Multilingual Named Entity Recognition

Home

Xlm Roberta Base Finetuned Panx All

Developed by transformersbook

A multilingual named entity recognition model fine-tuned on the PAN-X dataset based on XLM-RoBERTa-base

Sequence Labeling

Transformers

Open Source License:MIT #Multilingual NER #High-precision entity recognition #Cross-lingual transfer learning

Downloads 15

Release Time : 3/2/2022

Model Overview

This model is optimized for multilingual named entity recognition tasks, based on the XLM-RoBERTa-base architecture and fine-tuned on the PAN-X dataset. It is primarily used to identify named entities in text, such as person names, place names, organization names, etc.

Model Features

Multilingual support

Based on the XLM-RoBERTa architecture, it supports named entity recognition in multiple languages

High accuracy

Achieves 84.32% accuracy and 84.89% F1 score on the WikiANN test set

Transfer learning

Obtains excellent named entity recognition capabilities by fine-tuning on a large-scale pre-trained model

Model Capabilities

Named Entity Recognition

Multilingual text processing

Sequence labeling

Use Cases

Natural Language Processing

Multilingual text entity extraction

Identify and extract entities such as person names, place names, and organization names from multilingual text

Achieves an F1 score of 0.8489 on the WikiANN test set

Information extraction system

Serves as a core component of an information extraction system to automatically identify key entities in text

🚀 xlm-roberta-base-finetuned-panx-all

This model is a fine - tuned version of [xlm - roberta - base](https://huggingface.co/xlm - roberta - base) on the PAN - X dataset, trained in the context of multilingual named entity recognition.

🚀 Quick Start

This model is a fine - tuned version of [xlm - roberta - base](https://huggingface.co/xlm - roberta - base) on the PAN - X dataset. The model is trained in Chapter 4: Multilingual Named Entity Recognition in the [NLP with Transformers book](https://learning.oreilly.com/library/view/natural - language - processing/9781098103231/). You can find the full code in the accompanying [Github repository](https://github.com/nlp - with - transformers/notebooks/blob/main/04_multilingual - ner.ipynb).

It achieves the following results on the evaluation set:

Loss: 0.1739
F1: 0.8581

📚 Documentation

Model Information

Property	Details
Model Type	Fine - tuned version of xlm - roberta - base on the PAN - X dataset
Training Data	PAN - X dataset
Metrics on Evaluation Set	Loss: 0.1739, F1: 0.8581

Model Index

Name: xlm - roberta - base - finetuned - panx - all
Results:
- Task:
  - Type: token - classification
  - Name: Token Classification
- Dataset:
  - Name: wikiann
  - Type: wikiann
  - Config: en
  - Split: test
- Metrics:
  - Accuracy: 0.843189280620875
  - Precision: 0.8410061269097046
  - Recall: 0.8568527450211155
  - F1: 0.8488554853827908
  - Loss: 0.6632214784622192

Training Procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e - 05
train_batch_size: 24
eval_batch_size: 24
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.2912	1.0	835	0.1883	0.8238
0.1548	2.0	1670	0.1738	0.8480
0.101	3.0	2505	0.1739	0.8581

Framework versions

Transformers 4.12.0.dev0
Pytorch 1.9.1+cu102
Datasets 1.12.1
Tokenizers 0.10.3

📄 License

This model is released under the MIT license.

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