tomaarsen/span-marker-bert-small-orgs

SpanMarker with prajjwal1/bert-small on FewNERD, CoNLL2003, and OntoNotes v5

This is a SpanMarker model trained on the FewNERD, CoNLL2003, and OntoNotes v5 dataset that can be used for Named Entity Recognition. This SpanMarker model uses prajjwal1/bert-small as the underlying encoder.

Model Details

Model Description

• Model Type: SpanMarker
• Encoder: prajjwal1/bert-small
• Maximum Sequence Length: 256 tokens
• Maximum Entity Length: 8 words
• Training Dataset: FewNERD, CoNLL2003, and OntoNotes v5
• Language: en
• License: cc-by-sa-4.0

Model Sources

• Repository: SpanMarker on GitHub
• Thesis: SpanMarker For Named Entity Recognition

Model Labels

Label	Examples
ORG	"Texas Chicken", "Church 's Chicken", "IAEA"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.7618	0.7478	0.7547
ORG	0.7618	0.7478	0.7547

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-small-orgs")
# Run inference
entities = model.predict("American Motors included Chinese officials as part of the negotiations establishing Beijing Jeep (now Beijing Benz).")

Downstream Use

You can finetune this model on your own dataset.

Click to expand

from span_marker import SpanMarkerModel, Trainer

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-small-orgs")

# Specify a Dataset with "tokens" and "ner_tag" columns
dataset = load_dataset("conll2003") # For example CoNLL2003

# Initialize a Trainer using the pretrained model & dataset
trainer = Trainer(
    model=model,
    train_dataset=dataset["train"],
    eval_dataset=dataset["validation"],
)
trainer.train()
trainer.save_model("tomaarsen/span-marker-bert-small-orgs-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	1	23.5706	263
Entities per sentence	0	0.7865	39

Training Hyperparameters

• learning_rate: 0.0001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training Results

Epoch	Step	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy
0.5720	600	0.0076	0.7642	0.6630	0.7100	0.9656
1.1439	1200	0.0070	0.7705	0.7139	0.7411	0.9699
1.7159	1800	0.0067	0.7837	0.7231	0.7522	0.9709
2.2879	2400	0.0070	0.7768	0.7517	0.7640	0.9725
2.8599	3000	0.0068	0.7877	0.7374	0.7617	0.9718

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.068 kg of CO2
• Hours Used: 0.52 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.9.16
• SpanMarker: 1.5.1.dev
• Transformers: 4.30.0
• PyTorch: 2.0.1+cu118
• Datasets: 2.14.0
• Tokenizers: 0.13.3

Citation

BibTeX

@software{Aarsen_SpanMarker,
    author = {Aarsen, Tom},
    license = {Apache-2.0},
    title = {{SpanMarker for Named Entity Recognition}},
    url = {https://github.com/tomaarsen/SpanMarkerNER}
}