Seeking Paper or Detailed Documentation for paraphrase-mpnet-base-v2-fuzzy-matcher
Hi @shahrukhx01 👋
I hope you’re doing well! I’ve been exploring your paraphrase-mpnet-base-v2-fuzzy-matcher model and am really impressed by how it handles character-level fuzzy matching. I’d love to learn more about your approach:
Which datasets or synthetic typo-pair generators did you use to fine-tune MPNet for this task? If you’re able to share any of that data, I’d be very grateful!
Have you written a short paper, blog post, or technical note describing your methodology?
If so, could you please upload it or point me to where I can read it?
What similarity thresholds do you recommend for different fuzzy-matching scenarios?
Thank you so much for sharing this excellent work! I’m really looking forward to any insights or resources you can provide.
Cheers,