AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Self-supervised and Supervised Joint Training for Resource-rich Machine Translation

Yong Cheng, Wei Wang, Lu Jiang, Wolfgang Macherey

ICML 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised speech and brain decoding · 8 citations (OpenAlex)

This paper tried a common change: Add dropout

apply attention dropout and use model predictions in crossover-label computation · WMT'14 En→De · BLEU: 29.87 -> 30.46 Improved

What 795 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
jointly train with F2-XEnDec rather than the reproduced TransformerTransformer-big · WMT'14 En→DeBLEU: 30.88 -> 31.60Improved
jointly train with F2-XEnDec rather than the reproduced TransformerTransformer-big · WMT'14 De→EnBLEU: 33.12 -> 34.94Improved
jointly train with F2-XEnDec rather than Joint Training with BARTTransformer-big · WMT'14 En→FrBLEU: 44.18 -> 45.15Improved
jointly train with F2-XEnDec rather than the reproduced TransformerTransformer-big · WMT'14 Fr→EnBLEU: 39.82 -> 41.60Improved
add the instance-level fusion loss L_F2 (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 29.21 -> 30.46; -1.25 BLEU pointsImproved
add the monolingual self-supervised loss L_F1 (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 29.55 -> 30.46Improved
use XEnDec with both parallel and monolingual inputs instead of parallel-only XEnDec (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 29.23 -> 30.46Improved
use crossover mixing rather than Mixup for the second XEnDec (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 29.67 -> 30.46Improved
apply attention dropout and use model predictions in crossover-label computation (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 29.87 -> 30.46Improved
use model predictions when computing crossover labels (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 30.24 -> 30.46Improved
increase monolingual data from size ×5 to ×10 (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 30.46 -> 30.22Hurt
increase monolingual data from size ×1 to ×5 (ablation)F2-XEnDec · WMT'14 En→DeBLEU: 29.84 -> 30.46Improved

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