atlas

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

Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework

ICLR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Combine unsupervised joint initialization, vocabulary reallocation, and RCSLS alignment refinementJoint_Align · MUSE BLIP@1 avg: 72.4 -> 74.5Helped
Add vocabulary reallocation to unsupervised joint training, without alignment refinement (ablation)Unsupervised Joint · MUSE BLIP@1 avg: 29.3 -> 42.3Helped
Remove vocabulary reallocation while using RCSLS refinement (ablation)Joint_Align + RCSLS · MUSE BLIP@1 avg: 74.5 -> 29.0Hurt
Add a seed dictionary and randomly replace corpus words with their translationsUnsupervised Joint · MUSE BLIP@1 avg: 29.3 -> 42.0Helped
Add alignment refinement to M-BERT extracted featuresM-BERT Feature · CoNLL cross-lingual NERF1 avg: 73.50 -> 75.11Helped

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