Viet-Anh on Software Logo

What is: DeCLUTR?

SourceDeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

DeCLUTR is an approach for learning universal sentence embeddings that utilizes a self-supervised objective that does not require labelled training data. The objective learns universal sentence embeddings by training an encoder to minimize the distance between the embeddings of textual segments randomly sampled from nearby in the same document.