mlsanityData to 14 Oct 2026

Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer

arXiv 2309.10891 ↗First posted 19 Sep 2023cs.CL cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in languages with more sufficient training resources to generalize to other low-resource languages. Earlier efforts on this task use parallel corpora, bilingual dictionaries, or other annotated alignment data to improve cross-lingual transferability, which are typically expensive to obtain. In this paper, we propose a simple yet effective method, SALT, to improve the zero-shot cross-lingual transfer of the multilingual pretrained language models without the help of such external data. By incorporating code-switching and embedding mixup with self-augmentation, SALT effectively distills cross-lingual knowledge from the multilingual PLM and enhances its transferability on downstream tasks. Experimental results on XNLI and PAWS-X show that our method is able to improve zero-shot cross-lingual transferability without external data. Our code is available at https://github.com/luka-group/SALT.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 35 of its 42 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

35 of 42 references.

References · 35

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  5. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  6. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  8. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  9. 2019How multilingual is Multilingual BERT?cited by 645
  10. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  11. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 578
  12. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
23 more
  1. 2018Generating Natural Language Adversarial Examplescited by 424
  2. 2021A Survey of Data Augmentation Approaches for NLPcited by 409
  3. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 340
  4. 2020InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Trainingcited by 237
  5. 2019Emerging Cross-lingual Structure in Pretrained Language Modelscited by 181
  6. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 168
  7. 2019Augmenting Data with Mixup for Sentence Classification: An Empirical Studycited by 125
  8. 2020Multilingual Alignment of Contextual Word Representationscited by 114
  9. 2021MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfercited by 90
  10. 2020CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLPcited by 79
  11. 2020Zero-Shot Cross-Lingual Transfer with Meta Learningcited by 66
  12. 2020On Learning Universal Representations Across Languagescited by 58
  13. 2020GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extractioncited by 43
  14. 2019Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systemscited by 42
  15. 2022Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extractioncited by 40
  16. 2022Enhancing Cross-lingual Transfer by Manifold Mixupcited by 30
  17. 2021Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Fillingcited by 25
  18. 2021Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoderscited by 24
  19. 2021Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Trainingcited by 21
  20. 2022Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structurecited by 17
  21. 2019Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsingcited by 11
  22. 2021Syntax-augmented Multilingual BERT for Cross-lingual Transfercited by 11
  23. 2020Identifying Necessary Elements for BERT's Multilingualitycited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2024Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switchingcited by 3
  2. 2025Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Transfer in Sense-Aware Taskscited by 0
  3. 2026Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varietiescited by 0