This is a SpanMarker model trained on the Acronym Identification dataset that can be used for Named Entity Recognition. This SpanMarker model uses bert-base-uncased as the underlying encoder. See train.py for the training script.

Is your data always capitalized correctly? Then consider using the cased variant of this model instead for better performance: tomaarsen/span-marker-bert-base-acronyms.

Model Details

Model Description

Model Type: SpanMarker
Encoder: bert-base-uncased
Maximum Sequence Length: 256 tokens
Maximum Entity Length: 8 words
Training Dataset: Acronym Identification
Language: en
License: apache-2.0

Model Sources

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

Model Labels

Label	Examples
long	"successive convex approximation", "controlled natural language", "Conversational Question Answering"
short	"SODA", "CNL", "CoQA"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.9339	0.9063	0.9199
long	0.9314	0.8845	0.9074
short	0.9352	0.9174	0.9262

Uses

Direct Use for Inference

python

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-base-uncased-acronyms")
# Run inference
entities = model.predict("compression algorithms like principal component analysis (pca) can reduce noise and complexity.")

Downstream Use

You can finetune this model on your own dataset.

Click to expand

python

from span_marker import SpanMarkerModel, Trainer

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

# 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-base-uncased-acronyms-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	4	32.3372	170
Entities per sentence	0	2.6775	24

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
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: 2

Training Results

Epoch	Step	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy
0.3120	200	0.0097	0.8999	0.8731	0.8863	0.9718
0.6240	400	0.0075	0.9163	0.8995	0.9078	0.9769
0.9360	600	0.0076	0.9079	0.9153	0.9116	0.9773
1.2480	800	0.0069	0.9267	0.9006	0.9135	0.9778
1.5601	1000	0.0065	0.9268	0.9044	0.9154	0.9782
1.8721	1200	0.0065	0.9279	0.9061	0.9168	0.9787

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Carbon Emitted: 0.031 kg of CO2
Hours Used: 0.272 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: 1.3.1.dev
Transformers: 4.30.0
PyTorch: 2.0.1+cu118
Datasets: 2.14.0
Tokenizers: 0.13.2

Citation

BibTeX

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