AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding

Yanru Qu, Dinghan Shen, Yelong Shen, Sandra Sajeev, Weizhu Chen, Jiawei Han

ICLR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 44 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Stack adversarial training over back-translation rather than use either transformation alone (ablation)RoBERTa-base · MNLI-m devaccuracy: 88.5 -> 88.8Improved
Mix back-translation and adversarial samples instead of using back-translation alone (ablation)RoBERTa-base · MNLI-m devaccuracy: 88.5 -> 88.6Improved
Add cutoff to the back-translation and adversarial stack (ablation)RoBERTa-base · MNLI-m devaccuracy: 88.8 -> 88.5Hurt
Put cutoff after the back-translation and adversarial stack (ablation)RoBERTa-base · MNLI-m devaccuracy: 88.8 -> 88.4Hurt
Randomly select among back-translation, cutoff, and adversarial training (ablation)RoBERTa-base · MNLI-m devaccuracy: 88.8 -> 88.4Hurt
Use CoDA instead of standard fine-tuningRoBERTa-large · GLUE devaverage: 88.9 -> 91.1Improved
Use the proposed contrastive objective rather than MoCoRoBERTa-base · QNLI devaccuracy: 93.3 -> 93.6Improved
Use the proposed contrastive objective rather than SupConRoBERTa-base · RTE devaccuracy: 80.5 -> 82.0Improved
Increase memory-bank size (ablation)CoDA contrastive objective · MNLI-m devaccuracyImproved
Apply contrastive regularization to different data augmentation approachesRoBERTa-base · QNLIperformanceImproved
Use CoDA rather than back-translation or adversarial training aloneRoBERTa-base · MNLI and QNLI low-resource settingsperformanceImproved

Later papers that compared with this method

4 later accepted papers report CoDA as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy