SOTAVerified

Cross-Lingual Transfer

Cross-lingual transfer refers to transfer learning using data and models available for one language for which ample such resources are available (e.g., English) to solve tasks in another, commonly more low-resource, language.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 661–670 of 782 papers

TitleStatusHype
A Unified System for Aggression Identification in English Code-Mixed and Uni-Lingual Texts—0
Exploring Benefits of Transfer Learning in Neural Machine Translation—0
A little perturbation makes a difference: Treebank augmentation by perturbation improves transfer parsing—0
Zero-Resource Cross-Lingual Named Entity RecognitionCode0
Towards Lingua Franca Named Entity Recognition with BERT—0
Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal ResourcesCode0
Can Monolingual Pretrained Models Help Cross-Lingual Classification?—0
Cross-Lingual Relevance Transfer for Document Retrieval—0
Emerging Cross-lingual Structure in Pretrained Language Models—0
Cross-lingual Transfer Learning with Data Selection for Large-Scale Spoken Language Understanding—0
Show:102550
← PrevPage 67 of 79Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1PaLM 2 (few-shot)Accuracy94.4—Unverified
2mT0-13BAccuracy84.45—Unverified
3RoBERTa Large (translate test)Accuracy76.05—Unverified
4BLOOMZAccuracy75.5—Unverified
5MAD-X BaseAccuracy60.94—Unverified
6mGPTAccuracy55.5—Unverified