YuriyGuts/kaggle-quora-question-pairs

My solution to Kaggle Quora Question Pairs competition (Top 2%, Private LB log loss 0.13497).

46
/ 100
Emerging

This project helps identify duplicate questions within large text datasets, ensuring that similar inquiries are grouped together. It takes in pairs of questions and outputs a prediction indicating whether they are duplicates or distinct. This is useful for anyone managing user-generated content, like forum moderators, social media analysts, or customer support knowledge base managers.

102 stars. No commits in the last 6 months.

Use this if you need to automatically detect and flag semantically similar questions in a large corpus of text to avoid redundancy or improve information retrieval.

Not ideal if you are looking for a simple, off-the-shelf solution without any setup or if your primary goal is not question deduplication.

content-moderation information-retrieval customer-support text-analytics data-quality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

102

Forks

38

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 26, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/YuriyGuts/kaggle-quora-question-pairs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.