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 421–430 of 782 papers

TitleStatusHype
Soft Alignment of Modality Space for End-to-end Speech Translation—0
Soft Language Clustering for Multilingual Model Pre-training—0
Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer—0
Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing—0
Specializing Distributional Vectors of All Words for Lexical Entailment—0
SpeechTaxi: On Multilingual Semantic Speech Classification—0
Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios—0
Stanceosaurus 2.0: Classifying Stance Towards Russian and Spanish Misinformation—0
Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi—0
Subword-based Cross-lingual Transfer of Embeddings from Hindi to Marathi and Nepali—0
Show:102550
← PrevPage 43 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