---
license: cc-by-nc-3.0
metrics:
- accuracy
- f1
- recall
- precision
base_model:
- distilbert/distilbert-base-uncased
tags:
- event_extraction
- email
---
# DistilBERT-based Named Entity Recognition (NER) Model for Event Extraction

This repository contains a fine-tuned `DistilBERT` model for extracting **event-related entities** such as:

- **Event Name**
- **Date**
- **Time**
- **Venue**

The model is trained on a custom NER dataset with the goal of accurately parsing event details from plain text, such as emails or notifications.

---

## Model Details

- **Base Model:** `distilbert-base-uncased`
- **Task:** Token Classification (NER)
- **Fine-Tuned On:** Custom annotated dataset for events
- **Framework:** [HuggingFace Transformers](https://huggingface.co/transformers/)
- **Library Versions:**
  - `transformers`: 4.25+
  - `datasets`: 2.10+
  - `torch`: 1.13+
  - `seqeval`: for evaluation metrics

---

## Labels Used

```text
EVENT_NAME
DATE
TIME
VENUE
O  # Outside any entity
```
---

## Contributors

- [Thiyaga158](https://huggingface.co/Thiyaga158)
- [Hansika08](https://huggingface.co/Hansika08)

---

## License

This model is licensed under [CC BY-NC 3.0](https://creativecommons.org/licenses/by-nc/3.0/).  
For research and educational use only.

---