PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Mini Project
Extractive Text Summariser
Picks the most important sentences using TextRank and TF-IDF scoring
1-2 weeks build
Overview
Builds a summary out of the document's own sentences. Each sentence is scored two ways, by TF-IDF weight and by TextRank centrality on a sentence-similarity graph, and the top-ranked ones are returned in their original order. A small web app lets you set the summary length and compare both methods on the same text.
What makes it stand up
- 01Two scoring methods implemented from first principles
- 02Sentence-similarity graph built with cosine similarity
- 03Adjustable summary length by sentence count or ratio
- 04ROUGE comparison of both methods on CNN/DailyMail samples
- 05Web interface for pasted text or uploaded .txt files
Module breakdown
- 01
Segmentation
Sentence splitting, tokenising and stop-word removal.
- 02
TF-IDF scorer
Scores sentences by the weight of the terms they contain.
- 03
TextRank
PageRank over a sentence graph weighted by similarity.
- 04
Evaluation
ROUGE-1, ROUGE-2 and ROUGE-L against reference summaries.
- 05
Web app
Flask front end with side-by-side method comparison.
After this, you will be able to
- Explain how PageRank transfers from web pages to sentences
- Contrast extractive and abstractive summarisation clearly
- Demo both methods on an article the examiner chooses
Technology stack
- Python
- NLTK
- scikit-learn
- NetworkX
- Flask
- Level
- Mini Project
- Domain
- Machine Learning
- 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