mlsanityData to 7 Oct 2026

CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP

arXiv 2006.06402 ↗First posted 11 Jun 2020cs.CLcited by 79

Not on the map. Why?

Abstract (arXiv)

Multi-lingual contextualized embeddings, such as multilingual-BERT (mBERT), have shown success in a variety of zero-shot cross-lingual tasks. However, these models are limited by having inconsistent contextualized representations of subwords across different languages. Existing work addresses this issue by bilingual projection and fine-tuning technique. We propose a data augmentation framework to generate multi-lingual code-switching data to fine-tune mBERT, which encourages model to align representations from source and multiple target languages once by mixing their context information. Compared with the existing work, our method does not rely on bilingual sentences for training, and requires only one training process for multiple target languages. Experimental results on five tasks with 19 languages show that our method leads to significantly improved performances for all the tasks compared with mBERT.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 20; 2023: 21; 2024: 10; 2025: 3; 2026: 3.

79 papers.

Sort:

By area:

  1. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  2. 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
  3. 2023Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languagescited by 96
  4. 2021Data Augmentation Approaches in Natural Language Processing: A Surveycited by 82
  5. 2021NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentationcited by 72
  6. 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
  7. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 49
  8. 2021ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversationcited by 43
  9. 2021MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NERcited by 42
  10. 2021Consistency Regularization for Cross-Lingual Fine-Tuningcited by 41
  11. 2024Understanding Cross-Lingual Alignment -- A Surveycited by 34
  12. 2022L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language Modelscited by 33
38 more
  1. 2023A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understandingcited by 31
  2. 2022Enhancing Cross-lingual Transfer by Manifold Mixupcited by 30
  3. 2021Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Fillingcited by 25
  4. 2021Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Trainingcited by 21
  5. 2021Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systemscited by 16
  6. 2023Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillationcited by 15
  7. 2022GL-CLeF: A Global-Local Contrastive Learning Framework for Cross-lingual Spoken Language Understandingcited by 14
  8. 2021Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triplescited by 13
  9. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
  10. 2021Cross-lingual Text Classification with Heterogeneous Graph Neural Networkcited by 12
  11. 2021XeroAlign: Zero-Shot Cross-lingual Transformer Alignmentcited by 11
  12. 2021Cross-lingual Intermediate Fine-tuning improves Dialogue State Trackingcited by 11
  13. 2023Enhancing Cross-lingual Transfer via Phonemic Transcription Integrationcited by 11
  14. 2022Textual Data Augmentation for Arabic-English Code-Switching Speech Recognitioncited by 10
  15. 2022EntityCS: Improving Zero-Shot Cross-lingual Transfer with Entity-Centric Code Switchingcited by 8
  16. 2021Are the Multilingual Models Better? Improving Czech Sentiment with Transformerscited by 7
  17. 2022CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understandingcited by 7
  18. 2022MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generationcited by 7
  19. 2022WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognitioncited by 7
  20. 2023Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translationcited by 7
  21. 2023Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizercited by 7
  22. 2023Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extractioncited by 6
  23. 2022Improving the Cross-Lingual Generalisation in Visual Question Answeringcited by 5
  24. 2023IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languagescited by 5
  25. 2021Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understandingcited by 4
  26. 2022A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learningcited by 4
  27. 2023HanoiT: Enhancing Context-aware Translation via Selective Contextcited by 4
  28. 2023Transfer-Free Data-Efficient Multilingual Slot Labelingcited by 4
  29. 2024CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scriptscited by 4
  30. 2025Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalitiescited by 4
  31. 2021Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languagescited by 3
  32. 2022Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understandingcited by 3
  33. 2022Few-shot News Recommendation via Cross-lingual Transfercited by 3
  34. 2022Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patternscited by 3
  35. 2022FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Taskscited by 3
  36. 2023Self-Augmentation Improves Zero-Shot Cross-Lingual Transfercited by 3
  37. 2024Zero-Shot Cross-Lingual Document-Level Event Causality Identification with Heterogeneous Graph Contrastive Transfer Learningcited by 3
  38. 2024Cross-Lingual Transfer for Natural Language Inference via Multilingual Prompt Translatorcited by 3

50 most cited of 79 All 79 (JSON)