AI Paper Atlas

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

Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Translation Model

Xuan-Phi Nguyen, Shafiq Joty, Kui Wu, AiTi Aw

NeurIPS 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 0 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
add stage 1 (language-specific decoder FFN finetuning) (ablation)CRISS · FLoRes En-NeBLEU: 5.5 -> 7.8Improved
add stage 1 (ablation)CRISS · FLoRes Gu-EnBLEU: 23.7 -> 26.2Improved
add stage 2 (separate English) after stage 1 (ablation)Ours · FLoRes Gu-EnBLEU: 26.2 -> 28.8Improved
add stage 2 after stage 1 (ablation)Ours · FLoRes En-EtBLEU: 17.4 -> 19.7Improved
add stage 3 after stage 2 (ablation)Ours · FLoRes En-LvBLEU: 16.3 -> 17.9Improved
add stage 4 after stage 3 in from-English direction (ablation)Ours · FLoRes En-GuBLEU: 16.8 -> 17.5Improved
add stage 4 after stage 3 in to-English direction (ablation)Ours · FLoRes Gu-EnBLEU: 29.5 -> 29.1No clear effect
add stage 4 after stage 3 in to-English direction (ablation)Ours · FLoRes Kk-EnBLEU: 20.0 -> 19.9No clear effect
add decoder language-specific FFN layers (ablation)Ours · FLoRes En-NeBLEU: 7.9 -> 8.8Improved
use language-specific attention instead of FFN in decoder (ablation)Ours · FLoRes En-NeBLEU: 8.8 -> 8.4Hurt
place language-specific FFN in encoder instead of decoder (ablation)Ours · FLoRes En-NeBLEU: 8.8 -> 6.5Hurt
add language-specific FFN to encoder as well as decoder (ablation)Ours · FLoRes En-NeBLEU: 8.8 -> 8.9No clear effect

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