SpanMarker with numind/generic-entity_recognition_NER-v1 on DFKI-SLT/few-nerd

This is a SpanMarker model trained on the DFKI-SLT/few-nerd dataset that can be used for Named Entity Recognition. This SpanMarker model uses numind/generic-entity_recognition_NER-v1 as the underlying encoder.

Model Details

Model Description

Model Type: SpanMarker
Encoder: numind/generic-entity_recognition_NER-v1
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 19 words
Training Dataset: DFKI-SLT/few-nerd
Language: en
License: mit

Model Sources

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

Model Labels

Label	Examples
art	"Time", "The Seven Year Itch", "Imelda de ' Lambertazzi"
building	"Boston Garden", "Sheremetyevo International Airport", "Henry Ford Museum"
event	"Iranian Constitutional Revolution", "Russian Revolution", "French Revolution"
location	"the Republic of Croatia", "Croatian", "Mediterranean Basin"
organization	"IAEA", "Texas Chicken", "Church 's Chicken"
other	"BAR", "Amphiphysin", "N-terminal lipid"
person	"Edmund Payne", "Hicks", "Ellaline Terriss"
product	"Phantom", "100EX", "Corvettes - GT1 C6R"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.7582	0.7751	0.7666
art	0.7713	0.7783	0.7748
building	0.6034	0.7085	0.6518
event	0.5512	0.5207	0.5355
location	0.8163	0.8321	0.8242
organization	0.7083	0.6894	0.6987
other	0.6748	0.7253	0.6991
person	0.8987	0.9053	0.9020
product	0.5685	0.6431	0.6035

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("span_marker_model_id")
# Run inference
entities = model.predict("Caretaker manager George Goss led them on a run in the FA Cup, defeating Liverpool in round 4, to reach the semi-final at Stamford Bridge, where they were defeated 2–0 by Sheffield United on 28 March 1925.")

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("span_marker_model_id")

# 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("span_marker_model_id-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	1	24.4956	163
Entities per sentence	0	2.5439	35

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 64
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
mixed_precision_training: Native AMP

Training Results

Epoch	Step	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy
1.7467	200	0.0120	0.7533	0.7473	0.7503	0.9286
3.4934	400	0.0110	0.7659	0.7761	0.7710	0.9385
5.2402	600	0.0114	0.7772	0.7899	0.7835	0.9424
6.9869	800	0.0120	0.7724	0.7953	0.7837	0.9421
8.7336	1000	0.0124	0.7680	0.7942	0.7809	0.9413

Framework Versions

Python: 3.10.12
SpanMarker: 1.5.0
Transformers: 4.35.2
PyTorch: 2.1.0+cu118
Datasets: 2.14.7
Tokenizers: 0.15.0

Citation

BibTeX

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

davanstrien
/

span-marker-bert-base-fewnerd-coarse-super