PopularMajor Project
Artificial Intelligence
Face Recognition Attendance System
Camera-based attendance with liveness detection and analytics
- Python
- OpenCV
- FaceNet
- Flask
- +2
₹4,900₹5,999
4.8/301 reviews
Artificial Intelligence · Mini Project
Named Entity Recognition
Tags people, places and organisations in news text
1-2 weeks build
Overview
Recognises people, organisations, locations and miscellaneous entities in news articles. A spaCy pipeline is trained on the public CoNLL-2003 dataset and then compared with a fine-tuned BERT token classifier, with entity-level precision, recall and F1 reported for each so the trade-off between speed and quality is visible.
What makes it stand up
- 01BIO tagging explained with worked examples
- 02spaCy pipeline and BERT token classifier on the same data
- 03Entity-level precision, recall and F1 per entity type
- 04Error analysis of boundary and type mistakes
- 05Colour-coded entity highlighting in a web demo
Module breakdown
- 01
Data
CoNLL-2003 loading and BIO label alignment.
- 02
spaCy model
Config-driven training with a custom pipeline.
- 03
BERT model
Token classification with subword label alignment.
- 04
Evaluation
Seqeval metrics and a confusion table by entity type.
- 05
Demo
Paste news text and see entities highlighted.
After this, you will be able to
- Explain BIO tagging and why subwords complicate it
- Compare the two models on speed and quality
- Demo tagging a news article chosen on the day
Technology stack
- Python
- spaCy
- Transformers
- Hugging Face
- Streamlit
- Level
- Mini Project
- Domain
- Artificial Intelligence
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support