# Zero-shot Cross-lingual Transfer is Under-specified Optimization

arXiv: https://arxiv.org/abs/2207.05666 · HTML: https://mlsanity.com/paper/2207.05666/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [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)
- [Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping](https://mlsanity.com/paper/2002.06305/) (2020)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines](https://mlsanity.com/paper/2006.04884/) (2020)
- [Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks](https://mlsanity.com/paper/1811.01088/) (2018)
- [Qualitatively characterizing neural network optimization problems](https://mlsanity.com/paper/1412.6544/) (2014)
- [Better Fine-Tuning by Reducing Representational Collapse](https://mlsanity.com/paper/2008.03156/) (2020)
- [Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models](https://mlsanity.com/paper/1909.11299/) (2019)
- [A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters](https://mlsanity.com/paper/2012.15682/) (2020)
- [Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction](https://mlsanity.com/paper/2109.06798/) (2021)

## Built on by (most cited first, 4 of 4)

- [Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a Solution](https://mlsanity.com/paper/2305.17325/) (2023)
- [MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue](https://mlsanity.com/paper/2212.10455/) (2022)
- [A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness](https://mlsanity.com/paper/2312.01082/) (2023)
- [DiTTO: A Feature Representation Imitation Approach for Improving Cross-Lingual Transfer](https://mlsanity.com/paper/2303.02357/) (2023)

## Abstract (arXiv)

Pretrained multilingual encoders enable zero-shot cross-lingual transfer, but often produce unreliable models that exhibit high performance variance on the target language. We postulate that this high variance results from zero-shot cross-lingual transfer solving an under-specified optimization problem. We show that any linear-interpolated model between the source language monolingual model and source + target bilingual model has equally low source language generalization error, yet the target language generalization error reduces smoothly and linearly as we move from the monolingual to bilingual model, suggesting that the model struggles to identify good solutions for both source and target languages using the source language alone. Additionally, we show that zero-shot solution lies in non-flat region of target language error generalization surface, causing the high variance.