Identifying duplicates in csv

Hello, I’m new to HuggingFace and learning how to leverage HF models to create solutions faster for data specific problems. I have been working on a use case that scans through the csv list of employees and find out the duplicates that has similar names/addresses/emails but not same. I’m trying to utilize semantic search or paraphrase mining to achieve this.

Please let me know whether we can do this with huggingface models or if so what would be the right approach to do this.