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
Spell Checker & Corrector
Finds misspellings and ranks corrections by edit distance and context
1-2 weeks build
Overview
A spelling corrector that generates candidates within one or two edits of a misspelt word, then ranks them with a unigram and bigram language model so the surrounding words influence the choice. Levenshtein distance is implemented by hand with dynamic programming, and a desktop editor underlines errors and offers fixes on click.
What makes it stand up
- 01Levenshtein distance written from scratch with a DP table
- 02Candidate generation by insert, delete, replace and transpose
- 03Bigram context ranking so 'there' and 'their' are chosen sensibly
- 04Evaluation on the public Birkbeck spelling error corpus
- 05Desktop editor with underlines and click-to-correct
Module breakdown
- 01
Dictionary
Word frequencies built from a large public text corpus.
- 02
Edit distance
Dynamic programming implementation with a traceback view.
- 03
Candidates
Edits-one and edits-two generation filtered by vocabulary.
- 04
Ranking
Unigram and bigram probabilities with smoothing.
- 05
Editor
Tkinter text editor with inline suggestions.
After this, you will be able to
- Fill in an edit-distance table by hand on the whiteboard
- Explain how context changes the chosen correction
- Demo correcting a paragraph the examiner types
Technology stack
- Python
- NLTK
- NumPy
- Tkinter
- 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