This model is a SpanMarker model fine-tuned for fine-grained Named Entity Recognition (NER) in the climate change research domain, extracting 28 distinct entity types. It utilizes the domain-specific P0L3/cliscibert_scivocab_uncased as the underlying encoder.

📌 Model Details

Model Type: SpanMarker
Encoder: P0L3/cliscibert_scivocab_uncased
Maximum Sequence Length: 512 tokens
Maximum Entity Length: 14 words
Language: English
License: cc-by-sa-4.0

Model Labels

Label	Examples
Asset	"raw material", "water resources", "mental health"
Body Part	"leaves", "plant leaves", "deep tissue compartment"
Body of Water	"rivers", "Dhaleshwari river", "peripheral rivers"
Chemical	"marine algal toxin", "domoic acid", "cathode materials"
Disease	"seizures", "chronic epileptic syndrome", "acute neurologic signs"
Ecosystem	"cloud forests", "polluted environment", "Tropical montane cloud forest"
Energy Source	"fossil fuels", "12-cell series battery-pack prototype", "battery cells"
Field of Study	"study", "reference laboratory", "veterinary medicine"
Geographical Feature	"heterogenous topography", "low point", "mountainous regions"
Intellectual Artefact	"Daily husbandry records", "data", "Veterinary medical records"
Location	"beaches", "wild", "Westbrook"
Mathematical Expression	"Stepwise machine hour constraints", "difference", "gradient"
Measuring Device	"station", "EEG", "MRI scan"
Meteorological Phenomenon	"climatic variability", "rainfall", "climate change"
Method	"serum monitoring", "clinical efficacy", "dosing"
Natural Disaster	"heavy metal contamination", "seasonal air pollution", "environmental pollution"
Natural Phenomenon	"biochemical changes", "changing ocean conditions", "algal blooms"
Organism	"California sea lions", "Zalophus californianus", "species"
Organization	"reference laboratory", "long-term care facility", "NOAA National Marine Fisheries Service"
Other	"normal eating", "reports", "marine mammal health"
Person	"clinicians", "staff", "Clinicians"
Physical Artefact	"electric vehicle", "EVs", "paved east – west road"
Physical Phenomenon	"seasonal changes", "structural abnormalities", "normal food intake"
Policy	"safety", "pollution", "energy security"
Quantity	"energy density", "200 mAhg − 1", ">"
Satellite	"Tropical Rainfall Measuring Mission", "satellites", "TRMM"
System	"climate", "global overturning circulation", "system structure"
Time Period	"several decades", "periods of prolonged anorexia", "101 days"

🚀 Main Results (Selected Checkpoint)

This repository provides the best-performing checkpoint selected from 5 runs with different random seeds. While the internal training logs tracked performance on the validation split of CliReNER_silver, the final model selection and the metrics below are evaluated on the independent, expert-annotated CliReNER_gold dataset.

Metric	Score
Precision	64.95
Recall	65.14
F1	65.04

This checkpoint corresponds to the seed with the highest strict F1 on the gold evaluation set.

📊 Results Across Seeds

We fine-tuned the model using 5 different random seeds to assess the stability and robustness of the architecture on the domain-specific text.

Seed	Precision	Recall	Strict F1
1	XX.XX	XX.XX	XX.XX
2	XX.XX	XX.XX	XX.XX
3	XX.XX	XX.XX	XX.XX
4	XX.XX	XX.XX	XX.XX
5	XX.XX	XX.XX	XX.XX

Summary:

F1: mean = XX.XX, std = XX.XX
Precision: mean = XX.XX, std = XX.XX
Recall: mean = XX.XX, std = XX.XX

Model Selection Strategy: The uploaded checkpoint is the single best seed (highest strict F1 on the gold dataset), ensuring strong real-world performance and high-fidelity alignment with domain-expert consensus.

📂 Dataset & Evaluation

Training Dataset: CliReNER_silver
- Splits used: Stratified 80:10:10 ratio (Train/Validation/Test). The 80% split was used for training.
Evaluation Dataset: CliReNER_gold
- Splits used: Evaluated on the combined 192 sentences (expert-annotated via Weighted Expert Voting).
Preprocessing:
- Texts were tokenized using the tokenizer corresponding to the CliSciBERT encoder.
- The dataset utilizes a flat NER schema (nested entities are excluded, and overlapping entities are resolved to the most relevant span).
Metric Details:
- F1 type: Strict F1 (Entity-level exact match).
- Evaluation was performed ensuring entities match both the exact boundary span and the exact semantic label to be considered correct.

⚖️ Precision vs Recall Behavior

(Note to author: Describe the model’s tendency here based on your results. Example: "The model exhibits a balanced precision and recall profile.")

⚙️ Usage

Direct Use for Inference

Because this model was trained using the SpanMarker framework, it requires the span_marker library for inference.

pip install span_marker

python

from span_marker import SpanMarkerModel

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("P0L3/CliReNER-cliscibert_scivocab_uncased")

# Run inference
text = "Furthermore, coastal environments face some of the most significant consequences, specifically the compounding risks of sea level rise paired with prolonged and more violent sea level extremes (Vilibi et al. 2025)."
entities = model.predict(text)

for entity in entities:
    print(f"Entity: {entity['span']} | Label: {entity['label']} | Score: {entity['score']:.4f}")

# Entity: coastal environments | Label: Location | Score: 0.2828
# Entity: sea level rise | Label: Physical Phenomenon | Score: 0.3816
# Entity: prolonged | Label: Other | Score: 0.2954
# Entity: sea level extremes | Label: Meteorological Phenomenon | Score: 0.3865
# Entity: Vilibi et al. | Label: Person | Score: 0.7611
# Entity: 2025 | Label: Time Period | Score: 0.9815

Downstream Use

You can easily continue fine-tuning this model on your own dataset.

Click to expand

python

from span_marker import SpanMarkerModel, Trainer
from datasets import load_dataset

# Download from the 🤗 Hub
model = SpanMarkerModel.from_pretrained("your-huggingface-username/your-model-name")

# Specify a Dataset with "tokens" and "ner_tags" columns
dataset = load_dataset("your_custom_dataset")

# 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	3	31.4819	97
Entities per sentence	1	7.0100	22

Training Hyperparameters

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 3012 (Note: This log corresponds to the specific seed run saved during training)
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: adamw_torch with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 20

Training Results (CliReNER_silver Validation Split)

Epoch	Step	Validation Loss	Validation Precision	Validation Recall	Validation F1	Validation Accuracy
1.0	62	0.1135	0.1	0.0029	0.0056	0.6069
2.0	124	0.0502	0.6183	0.3300	0.4303	0.7480
3.0	186	0.0417	0.6189	0.6198	0.6194	0.8298
4.0	248	0.0373	0.6740	0.6141	0.6426	0.8368
5.0	310	0.0427	0.6761	0.6169	0.6452	0.8419
6.0	372	0.0409	0.6871	0.6270	0.6557	0.8434
7.0	434	0.0502	0.6495	0.6514	0.6504	0.8455

Framework Versions

Python: 3.10.19
SpanMarker: 1.7.0
Transformers: 4.50.0
PyTorch: 2.9.1+cu126
Datasets: 3.0.0
Tokenizers: 0.21.4

📚 Citation

If you use this model or the CliReNER datasets in your research, please cite the project:

latex

@misc{poleksic2026named,
  author       = {Poleksić, Andrija and Martinčić-Ipšić, Sanda},
  title        = {Named Entity Recognition for Climate Change Research},
  year         = {2026},
  howpublished = {Research Square},
  note         = {Preprint}
}

Please also acknowledge the SpanMarker framework: