Papers › SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning

SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning

8 Oct 2022arXiv:2210.03963archive 2025-07-28

Dongsheng Zhu, Zhenyu Mao, Jinghui Lu, Rui Zhao, Fei Tan

Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a simple dropout mechanism (viewed as continuous augmentation) surprisingly dominates discrete augmentations such as cropping, word deletion, and synonym replacement as reported. To understand the underlying rationales, we revisit existing approaches and attempt to hypothesize the desiderata of reasonable data augmentation methods: balance of semantic consistency and expression diversity. We then develop three simple yet effective discrete sentence augmentation schemes: punctuation insertion, modal verbs, and double negation. They act as minimal noises at lexical level to produce diverse forms of sentences. Furthermore, standard negation is capitalized on to generate negative samples for alleviating feature suppression involved in contrastive learning. We experimented extensively with semantic textual similarity on diverse datasets. The results support the superiority of the proposed methods consistently. Our key code is available at https://github.com/Zhudongsheng75/SDA

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zhudongsheng75/sda officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive LearningData AugmentationDiversityNegationRepresentation LearningSemantic Textual SimilaritySentence

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DropoutSimCSE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections