REVIEW 5 cited by
SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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
Forward citations
Cited by 5 Pith papers
-
LumiGen: An LVLM-Enhanced Iterative Framework for Fine-Grained Text-to-Image Generation
An LVLM-driven iterative text-to-image framework whose claimed performance scores are explicitly labeled fictitious, so no empirical result is established.
-
LVLM-Composer's Explicit Planning for Image Generation
An image generation model that explicitly plans objects, attributes, locations, and relations before synthesizing the image, with reported gains on LongBench-T2I that cannot be verified from the paper.
-
MM-FusionNet: Context-Aware Dynamic Fusion for Multi-modal Fake News Detection with Large Vision-Language Models
MM-FusionNet uses bi-directional cross-modal attention and a dynamic gating network to weight text and image features for fake news detection, reporting 0.938 F1 on the private LMFND dataset.
-
VisuCraft: Enhancing Large Vision-Language Models for Complex Visual-Guided Creative Content Generation via Structured Information Extraction
A prompt-wrapper framework for vision-language models reports improved story and poetry generation on a private benchmark, without releasing code, data, or models.
-
Large Language Models for Zero-Shot Multicultural Name Recognition
A prompt-tuned LLM with data augmentation and cultural context prompts reportedly recognizes multicultural names at 93.1% accuracy and unseen names at 89.5%, but the evidence is not reproducible.
Discussion (0). Sign in to comment.