RETSim: Resilient and Efficient Text Similarity

2 code implementations • 28 Nov 2023 • Marina Zhang, Owen Vallis, Aysegul Bumin, Tanay Vakharia, Elie Bursztein

This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplicate text retrieval, clustering, and dataset deduplication tasks.

Adversarial Text Clustering +3