zhang19991111/specter2-spanmarker-STEM-NER

SpanMarker with allenai/specter2_base on my-data

This is a SpanMarker model that can be used for Named Entity Recognition. This SpanMarker model uses allenai/specter2_base as the underlying encoder.

Model Details

Model Description

• Model Type: SpanMarker
• Encoder: allenai/specter2_base
• Maximum Sequence Length: 256 tokens
• Maximum Entity Length: 8 words
• Language: en
• License: cc-by-sa-4.0

Model Sources

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

Model Labels

Label	Examples
Data	"Depth time - series", "defect", "an overall mitochondrial"
Material	"cross - shore measurement locations", "the subject 's fibroblasts", "COXI , COXII and COXIII subunits"
Method	"an approximation", "EFSA", "in vitro"
Process	"intake", "a significant reduction of synthesis", "translation"

Evaluation

Metrics

Label	Precision	Recall	F1
all	0.7108	0.6715	0.6906
Data	0.6591	0.6138	0.6356
Material	0.795	0.7910	0.7930
Method	0.5	0.45	0.4737
Process	0.6898	0.6293	0.6582

Uses

Direct Use for Inference

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("span-marker-allenai/specter2_base-me")
# Run inference
entities = model.predict("We established a P fertilizer need map based on integrating results from the two systems .")

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-allenai/specter2_base-me")

# 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-allenai/specter2_base-me-finetuned")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Sentence length	3	25.6049	106
Entities per sentence	0	5.2439	22

Training Hyperparameters

• learning_rate: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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: 10

Framework Versions

• Python: 3.10.12
• SpanMarker: 1.5.0
• Transformers: 4.36.2
• PyTorch: 2.0.1+cu118
• Datasets: 2.16.1
• 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}
}