README.md

---
base_model: sentence-transformers/all-mpnet-base-v2
library_name: sentence-transformers
pipeline_tag: text-retrieval
license: apache-2.0
tags:
- sentence-transformers
- text-retrieval
- feature-extraction
- work-domain
- skill-extraction
---

# ConTeXT-Skill-Extraction-base

This is a [sentence-transformers](https://www.SBERT.net) model based on the `all-mpnet-base-v2` architecture. It is designed for work-domain AI tasks, specifically skill extraction and normalization, as part of the **WorkRB** (Work Research Benchmark) framework.

The model is presented in the paper [WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain](https://huggingface.co/papers/2604.13055).

## Model Details

### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 768 dimensions
- **Similarity Function:** Cosine Similarity
- **License:** Apache 2.0

### Model Sources

- **Paper:** [WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain](https://huggingface.co/papers/2604.13055)
- **Repository:** [WorkRB on GitHub](https://github.com/techwolf-ai/WorkRB)
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)

## Usage

### Direct Usage (Sentence Transformers)

First, install the Sentence Transformers library:

```bash
pip install -U sentence-transformers
```

Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("jensjorisdecorte/ConTeXT-Skill-Extraction-base")

# Run inference
sentences = [
    'Proficient in Python programming and machine learning.',
    'Experienced in project management and agile methodologies.',
    'Knowledge of cloud computing and AWS infrastructure.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
```

## Full Model Architecture

```
SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```

## Training Details

### Framework Versions
- Python: 3.10.16
- Sentence Transformers: 3.4.0
- Transformers: 4.48.1
- PyTorch: 2.5.1+cpu
- Accelerate: 1.3.0
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## Citation

If you find this model useful, please consider citing the following work:

```bibtex
@misc{delange2025unifiedworkembeddings,
      title={Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker}, 
      author={Matthias De Lange and Jens-Joris Decorte and Jeroen Van Hautte},
      year={2025},
      eprint={2511.07969},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.07969}, 
}
```