SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.07847 · ACL · 2022

SCD: Self-Contrastive Decorrelation for Sentence Embeddings

Tassilo Klein

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging the contrast arising from the instantiation of standard dropout at different rates. The proposed method is conceptually simple yet empirically powerful. It achieves comparable results with state-of-the-art methods on multiple benchmarks without using contrastive pairs. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.07847")
get_code_for_paper("2203.07847")
have("2203.07847")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.07847.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.07847.svg)](https://syntology.ai/paper/2203.07847)

Connect an agent — have() is free.