Showing cs.CLShow all
2 papers · 1 filter
cs.CL2023
RETSim: Resilient and Efficient Text Similarity
Marina Zhang, Owen Vallis, Aysegul Bumin +2
This paper introduces RETSim (Resilient and Efficient Text Similarity), a lightweight, multilingual deep learning model trained to produce robust metric embeddings for near-duplica…
cs.CL2023
RETVec: Resilient and Efficient Text Vectorizer
Elie Bursztein, Marina Zhang, Owen Vallis +2
This paper describes RETVec, an efficient, resilient, and multilingual text vectorizer designed for neural-based text processing. RETVec combines a novel character encoding with an…