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
Keyword Extraction from Text
Compares RAKE, YAKE and KeyBERT on the same documents
1-2 weeks build
Overview
Runs three keyword extractors on the same text and measures how they differ. RAKE uses word co-occurrence, YAKE uses statistical features of each term, and KeyBERT ranks candidate phrases by embedding similarity to the whole document. All three are scored against the public Inspec dataset's human-assigned keywords.
What makes it stand up
- 01Three extraction methods behind a single interface
- 02RAKE implemented by hand so the maths is explainable
- 03Precision, recall and F1 at k against Inspec keywords
- 04Overlap chart showing where the methods agree
- 05Streamlit app with a method selector and highlighted output
Module breakdown
- 01
Preprocessing
Tokenising, stop-word lists and candidate phrase rules.
- 02
RAKE
Co-occurrence graph and degree-to-frequency scoring.
- 03
YAKE
Position, casing and frequency features per term.
- 04
KeyBERT
Embedding similarity with diversity reranking.
- 05
Evaluation
F1 at k and agreement analysis across methods.
After this, you will be able to
- Explain how each method decides a phrase matters
- Defend which method suits which kind of document
- Demo all three on a paragraph from the examiner
Technology stack
- Python
- KeyBERT
- NLTK
- scikit-learn
- 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