Papers › A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning

A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning

18 Oct 2022COLING 2022 10arXiv:2210.09934archive 2025-07-28

Kunbo Ding, Weijie Liu, Yuejian Fang, Weiquan Mao, Zhe Zhao, Tao Zhu, Haoyan Liu, Rong Tian, Yiren Chen

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training multilingual models on English-only resources and transferring them to low-resource languages. However, its effect is limited by the gap between embedding clusters of different languages. To address this issue, we propose Embedding-Push, Attention-Pull, and Robust targets to transfer English embeddings to virtual multilingual embeddings without semantic loss, thereby improving cross-lingual transferability. Experimental results on mBERT and XLM-R demonstrate that our method significantly outperforms previous works on the zero-shot cross-lingual text classification task and can obtain a better multilingual alignment.

PaperPDFConference PDFCode

Code

kb-ding/ear officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Lingual TransferText ClassificationTransfer LearningXLM-RZero-Shot Cross-Lingual Transfertext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

XLM-RmBERT

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections