mrm8488/bert-spanish-cased-finetuned-ner

Model

Spanish BERT (BETO) + NER

30 commits

3 linked in READMEs

updated May 20, 2021

See the code

README

Spanish BERT (BETO) + NER

This model is a fine-tuned on NER-C version of the Spanish BERT cased (BETO) for NER downstream task.

Details of the downstream task (NER) - Dataset

Dataset: CONLL Corpora ES

I preprocessed the dataset and split it as train / dev (80/20)

Dataset	# Examples
Train	8.7 K
Dev	2.2 K

Fine-tune on NER script provided by Huggingface
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)	90.17	420
Best Multilingual BERT	87.38	681
TinyBERT-spanish-uncased-finetuned-ner	70.00	55

Model in action

Fast usage with pipelines:

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'}]

Created by Manuel Romero/@mrm8488

Made with ♥ in Spain

bert

endpoints_compatible

pytorch

token-classification

transformers

Similar repos

mrm8488/TinyBERT-spanish-uncased-finetuned-ner

Model

Spanish TinyBERT + NER

dslim/bert-base-NER

Model

bert-base-NER

743

dccuchile/beto

BETO - Spanish version of the BERT model

507

dccuchile/bert-base-spanish-wwm-cased

Model

BETO: Spanish BERT

dccuchile/bert-base-spanish-wwm-uncased

Model

BETO: Spanish BERT

tomaarsen/span-marker-bert-base-fewnerd-fine-super

Model

SpanMarker with bert-base-cased on FewNERD

flair/ner-spanish-large

Model

Spanish NER in Flair (large model)

tomaarsen/span-marker-mbert-base-multinerd

Model

SpanMarker for Multilingual Named Entity Recognition

Linked in READMEs

huggingface/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in…

167,813

README badge

dccuchile/beto

BETO - Spanish version of the BERT model

507

README badge

EduardoProfe666/une-unwrapped-habana

⚡ UNE Unwrapped - Resumen Eléctrico de La Habana

README badge

mrm8488/bert-spanish-cased-finetuned-ner

Model

Spanish BERT (BETO) + NER

30 commits

3 linked in READMEs

updated May 20, 2021

See the code

README

Spanish BERT (BETO) + NER

This model is a fine-tuned on NER-C version of the Spanish BERT cased (BETO) for NER downstream task.

Details of the downstream task (NER) - Dataset

Dataset: CONLL Corpora ES

I preprocessed the dataset and split it as train / dev (80/20)

Dataset	# Examples
Train	8.7 K
Dev	2.2 K

Fine-tune on NER script provided by Huggingface
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)	90.17	420
Best Multilingual BERT	87.38	681
TinyBERT-spanish-uncased-finetuned-ner	70.00	55

Model in action

Fast usage with pipelines:

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'}]