| --- |
| language: en |
| license: cc-by-sa-4.0 |
| tags: |
| - span-marker |
| - token-classification |
| - ner |
| - named-entity-recognition |
| - generated_from_span_marker_trainer |
| - climate-change |
| - earth-science |
| widget: |
| - text: While a significant positive impact of solid-state cultivation using white |
| rot fungi on enzymatic digestibility was reported in some studies [68, 69], a |
| negative effect of fungal pretreatment on enzymatic hydrolysis was noted by investigators |
| like Shi et al . (2009) [33], who reported a glucose yield of 55 . 6 mg g − 1 |
| of cotton stalks pretreated with P . chrysosporium, which was approximately 17% |
| lower than the yield of untreated cotton stalks after enzymatic hydrolysis in |
| spite of significant lignin degradation. |
| - text: We quantify changes in the properties and amount of bottom water entering |
| the basin by combining repeat hydrographic observations, direct velocity measurements |
| and flow structure derived from a 0 . 1 ° global ocean sea-ice model that realistically |
| simulates AABW formation sites and export pathways. |
| - text: The impact of these differences on cloud forcing can be signi or more . cant |
| and as high as 30 W m In recent years, observations from satellite data have been |
| revised considerably after significant development efforts, especially after utilizing |
| new high-quality reference measurements from active sensors in space, and some |
| datasets have also improved polar cloud detection. |
| - text: If the response is significant, how does the solar forcing impact the EASM |
| rainfall variability? In this study, we will address these questions based on |
| the simulation results derived from one AD 850 control experiment (CTRL) and four |
| solar-only forcing experiments [spectral solar irradiance (SSI) experiments], |
| which were conducted by the Community Earth System (CESM-LME) Model – Last Millennium |
| Ensemble modeling project (Otto-Bliesner et al . 2016). |
| - text: Measurements from single moorings at each gateway reveal that the speed of |
| bottom water flow into the Australian Antarctic Basin varies with location, season |
| and density (Fig . 3a, c, e). |
| pipeline_tag: token-classification |
| library_name: span-marker |
| metrics: |
| - precision |
| - recall |
| - f1 |
| datasets: |
| - P0L3/CliReNER_v_1_1_28_SILVER |
| - P0L3/CliReNER_v_1_1_28_GOLD |
| base_model: allenai/scibert_scivocab_uncased |
| model-index: |
| - name: SpanMarker with allenai/scibert_scivocab_uncased |
| results: |
| - task: |
| type: token-classification |
| name: Named Entity Recognition |
| dataset: |
| name: CliReNER_silver |
| type: P0L3/CliReNER_v_1_1_28_SILVER |
| split: eval |
| metrics: |
| - type: f1 |
| value: 0.6542591267000716 |
| name: F1 |
| - type: precision |
| value: 0.6528571428571428 |
| name: Precision |
| - type: recall |
| value: 0.6556671449067432 |
| name: Recall |
| --- |
| |
| # SpanMarker-SciBERT for Climate Research NER |
|
|
| This model is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) 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 [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_scivocab_uncased) as the underlying encoder. |
|
|
| ## 📌 Model Details |
|
|
| - **Model Type:** SpanMarker |
| - **Encoder:** [allenai/scibert_scivocab_uncased](https://huggingface.co/allenai/scibert_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 | "mental health", "raw material", "water resources" | |
| | Body Part | "plant leaves", "deep tissue compartment", "leaves" | |
| | Body of Water | "peripheral rivers", "Dhaleshwari river", "rivers" | |
| | Chemical | "cathode materials", "domoic acid", "marine algal toxin" | |
| | Disease | "seizures", "chronic epileptic syndrome", "acute neurologic signs" | |
| | Ecosystem | "polluted environment", "Tropical montane cloud forest", "cloud forests" | |
| | Energy Source | "battery cells", "fossil fuels", "12-cell series battery-pack prototype" | |
| | Field of Study | "veterinary medicine", "study", "reference laboratory" | |
| | Geographical Feature | "mountainous regions", "heterogenous topography", "low point" | |
| | Intellectual Artefact | "Veterinary medical records", "Daily husbandry records", "data" | |
| | Location | "Westbrook", "beaches", "wild" | |
| | Mathematical Expression | "gradient", "Stepwise machine hour constraints", "difference" | |
| | Measuring Device | "EEG", "MRI scan", "station" | |
| | Meteorological Phenomenon | "climatic variability", "rainfall", "climate change" | |
| | Method | "serum monitoring", "clinical efficacy", "dosing" | |
| | Natural Disaster | "environmental pollution", "heavy metal contamination", "seasonal air pollution" | |
| | Natural Phenomenon | "biochemical changes", "algal blooms", "changing ocean conditions" | |
| | Organism | "Zalophus californianus", "species", "California sea lions" | |
| | Organization | "long-term care facility", "NOAA National Marine Fisheries Service", "reference laboratory" | |
| | Other | "normal eating", "reports", "marine mammal health" | |
| | Person | "Clinicians", "staff", "clinicians" | |
| | Physical Artefact | "electric vehicle", "paved east – west road", "EVs" | |
| | Physical Phenomenon | "seasonal changes", "structural abnormalities", "normal food intake" | |
| | Policy | "safety", "pollution", "energy security" | |
| | Quantity | "energy density", ">", "200 mAhg − 1" | |
| | Satellite | "TRMM", "satellites", "Tropical Rainfall Measuring Mission" | |
| | System | "global overturning circulation", "climate", "system structure" | |
| | Time Period | "periods of prolonged anorexia", "several decades", "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<sub>silver</sub>**, the final model selection and the metrics below are evaluated on the independent, expert-annotated **CliReNER<sub>gold</sub>** dataset. |
|
|
| | Metric | Score | |
| |------------|-------| |
| | Precision | XX.XX | |
| | Recall | XX.XX | |
| | F1 | XX.XX | |
|
|
| > 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<sub>silver</sub>](https://huggingface.co/datasets/P0L3/CliReNER_v_1_1_28_SILVER) |
| - **Splits used:** Stratified 80:10:10 ratio (Train/Validation/Test). The 80% split was used for training. |
| - **Evaluation Dataset:** [CliReNER<sub>gold</sub>](https://huggingface.co/datasets/P0L3/CliReNER_v_1_1_28_GOLD) |
| - **Splits used:** Evaluated on the combined 192 sentences (expert-annotated via Weighted Expert Voting). |
| - **Preprocessing:** |
| - Texts were tokenized using the standard SciBERT WordPiece tokenizer (`scivocab`). |
| - 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 slightly favors recall over precision" or "Balanced precision and recall")* |
|
|
| --- |
|
|
| ## ⚙️ Usage |
|
|
| ### Direct Use for Inference |
|
|
| Because this model was trained using the SpanMarker framework, it requires the `span_marker` library for inference. |
|
|
| ```bash |
| pip install span_marker |
| ``` |
|
|
| ```python |
| from span_marker import SpanMarkerModel |
| |
| # Download from the 🤗 Hub |
| model = SpanMarkerModel.from_pretrained("P0L3/CliReNER-scibert_scivocab_uncased") |
| |
| # Run inference |
| text = "At the same time, terrestrial systems are shifting as warming drives rapid changes in frozen soils. These soils, which cover 20% of the Earth’s land surface, are degrading, with cascading effects on water, energy, and carbon cycles (Zhao et al. 2026)." |
| entities = model.predict(text) |
| |
| for entity in entities: |
| print(f"Entity: {entity['span']} | Label: {entity['label']} | Score: {entity['score']:.4f}") |
| |
| # Entity: terrestrial systems | Label: System | Score: 0.6377 |
| # Entity: warming | Label: Physical Phenomenon | Score: 0.4777 |
| # Entity: frozen soils | Label: Geographical Feature | Score: 0.3317 |
| # Entity: soils | Label: Body of Water | Score: 0.3320 |
| # Entity: 20% | Label: Quantity | Score: 0.9814 |
| # Entity: Earth | Label: Location | Score: 0.9857 |
| # Entity: land surface | Label: Geographical Feature | Score: 0.5472 |
| # Entity: degrading | Label: Other | Score: 0.4863 |
| # Entity: energy | Label: Chemical | Score: 0.4364 |
| # Entity: water | Label: Chemical | Score: 0.6675 |
| # Entity: carbon cycles | Label: Physical Phenomenon | Score: 0.6238 |
| # Entity: Zhao et al. | Label: Person | Score: 0.8318 |
| # Entity: 2026 | Label: Time Period | Score: 0.9117 |
| |
| ``` |
|
|
| ### Downstream Use |
|
|
| You can easily continue fine-tuning this model on your own dataset. |
|
|
| <details><summary>Click to expand</summary> |
|
|
| ```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") |
| ``` |
| </details> |
|
|
| --- |
|
|
| ## 📉 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:** 0 |
| - **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<sub>silver</sub> Validation Split) |
| |
| | Epoch | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy | |
| |:-----:|:----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:| |
| | 1.0 | 62 | 0.1052 | 0.0 | 0.0 | 0.0 | 0.6075 | |
| | 2.0 | 124 | 0.0534 | 0.5492 | 0.4648 | 0.5035 | 0.7995 | |
| | 3.0 | 186 | 0.0392 | 0.7086 | 0.5409 | 0.6135 | 0.8201 | |
| | 4.0 | 248 | 0.0415 | 0.6404 | 0.6184 | 0.6292 | 0.8374 | |
| | 5.0 | 310 | 0.0382 | 0.6823 | 0.6471 | 0.6642 | 0.8513 | |
| | 6.0 | 372 | 0.0449 | 0.6888 | 0.6098 | 0.6469 | 0.8468 | |
| | 7.0 | 434 | 0.0483 | 0.6611 | 0.6298 | 0.6451 | 0.8498 | |
| | 8.0 | 496 | 0.0497 | 0.6529 | 0.6557 | 0.6543 | 0.8531 | |
| |
| ### Framework Versions |
| - **Python:** 3.10.19 |
| - **SpanMarker:** 1.7.0 |
| - **Transformers:** 4.50.0 |
| - **PyTorch:** 2.9.1 |
| - **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: |
| |
| ```latex |
| @software{Aarsen_SpanMarker, |
| author = {Aarsen, Tom}, |
| license = {Apache-2.0}, |
| title = {{SpanMarker for Named Entity Recognition}}, |
| url = {https://github.com/tomaarsen/SpanMarkerNER} |
| } |
| ``` |
