BERT Spanish Cased Finetuned NER Open-Source Model - Free Deployment for Precise Identification of Spanish Named Entities

Bert Spanish Cased Finetuned Ner

Developed by mrm8488

A fine-tuned version based on the Spanish BERT cased model (BETO) on the NER-C dataset, specifically designed for Named Entity Recognition (NER) tasks.

Sequence Labeling Spanish#Spanish NER #High-precision entity recognition #BERT fine-tuning

Downloads 77.49k

Release Time : 3/2/2022

Model Overview

This model is a fine-tuned Named Entity Recognition model based on Spanish BERT (BETO), capable of identifying entities such as person names, locations, and organization names in Spanish texts.

Model Features

High-performance Spanish NER

Achieves an F1 score of 90.17 on Spanish NER tasks, outperforming similar models.

Based on BETO model

Uses the Spanish pre-trained BERT model (BETO) as the foundation, with excellent language understanding capabilities.

Lightweight

The model size is only 420MB, making it more lightweight compared to multilingual BERT models.

Model Capabilities

Spanish text entity recognition

Identifies entities such as person names, locations, and organization names

Use Cases

Text analysis

News text entity extraction

Extract key entity information from Spanish news

Accurately identifies people, places, and organizations in news

Social media analysis

Analyze entity information in Spanish social media content

Helps understand key entities in social media discussions

🚀 Spanish BERT (BETO) + NER

This model is a fine - tuned version of the Spanish BERT cased (BETO) on NER - C for the NER downstream task. It aims to enhance the performance of named - entity recognition in Spanish text.

🚀 Quick Start

Basic Usage

from transformers import pipeline

nlp_ner = pipeline(
    "ner",
    model="mrm8488/bert-spanish-cased-finetuned-ner",
    tokenizer=(
        'mrm8488/bert-spanish-cased-finetuned-ner',  
        {"use_fast": False}
))

text = 'Mis amigos están pensando viajar a Londres este verano'

nlp_ner(text)

#Output: [{'entity': 'B-LOC', 'score': 0.9998720288276672, 'word': 'Londres'}]

✨ Features

Fine - tuned on NER: The model is specifically fine - tuned for the NER downstream task, which can effectively identify named entities in Spanish text.
Rich Label Coverage: It can recognize multiple types of named entities, including locations, organizations, persons, and miscellaneous entities.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline

nlp_ner = pipeline(
    "ner",
    model="mrm8488/bert-spanish-cased-finetuned-ner",
    tokenizer=(
        'mrm8488/bert-spanish-cased-finetuned-ner',  
        {"use_fast": False}
))

text = 'Mis amigos están pensando viajar a Londres este verano'

nlp_ner(text)

#Output: [{'entity': 'B-LOC', 'score': 0.9998720288276672, 'word': 'Londres'}]

📚 Documentation

Details of the downstream task (NER) - Dataset

Dataset: CONLL Corpora ES. The dataset was preprocessed and split into train / dev sets (80/20). | Dataset | # Examples | | ---- | ---- | | Train | 8.7 K | | Dev | 2.2 K |
Fine - tuning Script: [Fine - tune on NER script provided by Huggingface](https://github.com/huggingface/transformers/blob/master/examples/token - classification/run_ner_old.py)
Labels covered:

B - LOC
B - MISC
B - ORG
B - PER
I - LOC
I - MISC
I - ORG
I - PER
O

Metrics on evaluation set

Metric	# score
F1	90.17
Precision	89.86
Recall	90.47

Comparison

Model	# F1 score	Size(MB)
bert - base - spanish - wwm - cased (BETO)	88.43	421
[bert - spanish - cased - finetuned - ner (this one)](https://huggingface.co/mrm8488/bert - spanish - cased - finetuned - ner)	90.17	420
Best Multilingual BERT	87.38	681
[TinyBERT - spanish - uncased - finetuned - ner](https://huggingface.co/mrm8488/TinyBERT - spanish - uncased - finetuned - ner)	70.00	55

🔧 Technical Details

The model is based on the Spanish BERT cased (BETO) and is fine - tuned on the NER - C dataset for the NER downstream task. The fine - tuning process uses the script provided by Huggingface.

📄 License

No license information is provided in the original document.

Created by Manuel Romero/@mrm8488 Made with ♥ in Spain

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