# Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training

arXiv: https://arxiv.org/abs/2104.08645 · HTML: https://mlsanity.com/paper/2104.08645/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 63 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 30 of 47)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [Generating Natural Language Adversarial Examples](https://mlsanity.com/paper/1804.07998/) (2018)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [Adversarial Example Generation with Syntactically Controlled Paraphrase Networks](https://mlsanity.com/paper/1804.06059/) (2018)
- [PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification](https://mlsanity.com/paper/1908.11828/) (2019)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [Cross-Lingual Ability of Multilingual BERT: An Empirical Study](https://mlsanity.com/paper/1912.07840/) (2019)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Certified Robustness to Adversarial Word Substitutions](https://mlsanity.com/paper/1909.00986/) (2019)
- [Counter-fitting Word Vectors to Linguistic Constraints](https://mlsanity.com/paper/1603.00892/) (2016)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)
- [Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation](https://mlsanity.com/paper/1909.01492/) (2019)
- [CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP](https://mlsanity.com/paper/2006.06402/) (2020)

## Built on by (most cited first, 21 of 21)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [LLM-powered Data Augmentation for Enhanced Cross-lingual Performance](https://mlsanity.com/paper/2305.14288/) (2023)
- [Multilingual Generative Language Models for Zero-Shot Cross-Lingual Event Argument Extraction](https://mlsanity.com/paper/2203.08308/) (2022)
- [Understanding Cross-Lingual Alignment -- A Survey](https://mlsanity.com/paper/2404.06228/) (2024)
- [Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation](https://mlsanity.com/paper/2112.03473/) (2021)
- [Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise](https://mlsanity.com/paper/2109.06772/) (2021)
- [Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval](https://mlsanity.com/paper/2204.02292/) (2022)
- [Analyzing the Evaluation of Cross-Lingual Knowledge Transfer in Multilingual Language Models](https://mlsanity.com/paper/2402.02099/) (2024)
- [Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages](https://mlsanity.com/paper/2303.17683/) (2023)
- [Contextual Label Projection for Cross-Lingual Structured Prediction](https://mlsanity.com/paper/2309.08943/) (2023)
- [WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition](https://mlsanity.com/paper/2212.03506/) (2022)
- [Code-Switched Text Synthesis in Unseen Language Pairs](https://mlsanity.com/paper/2305.16724/) (2023)
- [A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base](https://mlsanity.com/paper/2405.11125/) (2024)
- [A Corpus for Sentence-level Subjectivity Detection on English News Articles](https://mlsanity.com/paper/2305.18034/) (2023)
- [A Simple and Effective Method to Improve Zero-Shot Cross-Lingual Transfer Learning](https://mlsanity.com/paper/2210.09934/) (2022)
- [Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering](https://mlsanity.com/paper/2109.12028/) (2021)
- [Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer](https://mlsanity.com/paper/2309.10891/) (2023)
- [Language Steering for Multilingual In-Context Learning](https://mlsanity.com/paper/2602.02326/) (2026)
- [Generalization Measures for Zero-Shot Cross-Lingual Transfer](https://mlsanity.com/paper/2404.15928/) (2024)
- [Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2501.14144/) (2025)
- [Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties](https://mlsanity.com/paper/2605.04500/) (2026)

## Abstract (arXiv)

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contextual embedding spaces such that even if the representations of different languages are not aligned well, the model can still achieve good performance on zero-shot cross-lingual transfer. In this work, we propose a learning strategy for training robust models by drawing connections between adversarial examples and the failure cases of zero-shot cross-lingual transfer. We adopt two widely used robust training methods, adversarial training and randomized smoothing, to train the desired robust model. The experimental results demonstrate that robust training improves zero-shot cross-lingual transfer on text classification tasks. The improvement is more significant in the generalized cross-lingual transfer setting, where the pair of input sentences belong to two different languages.