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 451–475 of 782 papers

TitleStatusHype
mLUKE: The Power of Entity Representations in Multilingual Pretrained Language ModelsCode1
Composable Sparse Fine-Tuning for Cross-Lingual TransferCode1
Learning Compact Metrics for MTCode1
K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and SyllablesCode1
Unsupervised Cross-Lingual Transfer of Structured Predictors without Source DataCode0
Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0—0
Cross-Language Learning for Entity MatchingCode0
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning—0
Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings—0
Analyzing the Effects of Reasoning Types on Cross-Lingual Transfer PerformanceCode0
Universal Recurrent Neural Network Grammar—0
Learning Invariant Representations on Multilingual Language Models for Unsupervised Cross-Lingual Transfer—0
Call Larisa Ivanovna: Code-Switching Fools Multilingual NLU ModelsCode0
Cross-lingual Intermediate Fine-tuning improves Dialogue State TrackingCode0
Visually Grounded Reasoning across Languages and CulturesCode1
Rumour Detection via Zero-shot Cross-lingual Transfer Learning—0
Simple and Effective Zero-shot Cross-lingual Phoneme RecognitionCode0
Cross-Lingual Language Model Meta-Pretraining—0
Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction—0
Cross-lingual Transfer of Monolingual Models—0
On the Universality of Deep Contextual Language Models—0
Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise—0
xGQA: Cross-Lingual Visual Question AnsweringCode1
AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African LanguagesCode0
Efficient Test Time Adapter Ensembling for Low-resource Language VarietiesCode1
Show:102550
← PrevPage 19 of 32Next →

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