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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 521–530 of 782 papers

Title	Date	Tasks	Status	Hype
Multilingual and Zero-Shot is Closing in on Monolingual Web Register Classification	May 1, 2021	ArticlesCross-Lingual Transfer	—Unverified	0
X-METRA-ADA: Cross-lingual Meta-Transfer Learning Adaptation to Natural Language Understanding and Question Answering	Apr 20, 2021	Cross-Lingual TransferMeta-Learning	CodeCode Available	1
Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders	Apr 18, 2021	Cross-Lingual TransferDecoder	CodeCode Available	0
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages	Apr 18, 2021	Cross-Lingual TransferNatural Language Understanding	CodeCode Available	0
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems	Apr 17, 2021	Cross-Lingual TransferMachine Translation	—Unverified	0
Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training	Apr 17, 2021	Cross-Lingual TransferSentence	CodeCode Available	0
"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks	Apr 16, 2021	Cross-Lingual TransferCross-Lingual Word Embeddings	CodeCode Available	0
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning	Apr 16, 2021	Cross-Lingual TransferMeta-Learning	CodeCode Available	1
Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing	Apr 15, 2021	Cross-Lingual TransferDecoder	—Unverified	0
XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation	Apr 15, 2021	Cross-Lingual TransferDiagnostic	CodeCode Available	1

Show:10 25 50

← PrevPage 53 of 79Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	PaLM 2 (few-shot)	Accuracy	94.4	—	Unverified
2	mT0-13B	Accuracy	84.45	—	Unverified
3	RoBERTa Large (translate test)	Accuracy	76.05	—	Unverified
4	BLOOMZ	Accuracy	75.5	—	Unverified
5	MAD-X Base	Accuracy	60.94	—	Unverified
6	mGPT	Accuracy	55.5	—	Unverified