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 341–350 of 782 papers

TitleStatusHype
Punctuation Restoration in Spanish Customer Support Transcripts using Transfer Learning—0
Discovering Language-neutral Sub-networks in Multilingual Language ModelsCode0
Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual GenerationCode2
Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages—0
Analyzing the Mono- and Cross-Lingual Pretraining Dynamics of Multilingual Language Models—0
The Importance of Being Parameters: An Intra-Distillation Method for Serious GainsCode1
Local Byte Fusion for Neural Machine TranslationCode0
The Geometry of Multilingual Language Model RepresentationsCode1
Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for MalteseCode1
Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented DialogCode0
Show:102550
← PrevPage 35 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