# Cross-Lingual Text Classification with Multilingual Distillation and Zero-Shot-Aware Training

arXiv: https://arxiv.org/abs/2202.13654 · HTML: https://mlsanity.com/paper/2202.13654/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 28 Feb 2022.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (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)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [On the Cross-lingual Transferability of Monolingual Representations](https://mlsanity.com/paper/1910.11856/) (2019)
- [MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00052/) (2020)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Revisiting Pre-Trained Models for Chinese Natural Language Processing](https://mlsanity.com/paper/2004.13922/) (2020)
- [InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training](https://mlsanity.com/paper/2007.07834/) (2020)
- [The Multilingual Amazon Reviews Corpus](https://mlsanity.com/paper/2010.02573/) (2020)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks](https://mlsanity.com/paper/1909.00964/) (2019)
- [Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language](https://mlsanity.com/paper/2004.12440/) (2020)
- [Multilingual BERT Post-Pretraining Alignment](https://mlsanity.com/paper/2010.12547/) (2020)
- [FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding](https://mlsanity.com/paper/2009.05166/) (2020)
- [TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing](https://mlsanity.com/paper/2002.12620/) (2020)
- [Orthogonal Language and Task Adapters in Zero-Shot Cross-Lingual Transfer](https://mlsanity.com/paper/2012.06460/) (2020)
- [Cross-lingual Distillation for Text Classification](https://mlsanity.com/paper/1705.02073/) (2017)
- [Sources of Transfer in Multilingual Named Entity Recognition](https://mlsanity.com/paper/2005.00847/) (2020)
- [Can Monolingual Pretrained Models Help Cross-Lingual Classification?](https://mlsanity.com/paper/1911.03913/) (2019)

## Built on by (most cited first, 3 of 3)

- [Too Brittle To Touch: Comparing the Stability of Quantization and Distillation Towards Developing Lightweight Low-Resource MT Models](https://mlsanity.com/paper/2210.15184/) (2022)
- [Mitigating Language-Level Performance Disparity in mPLMs via Teacher Language Selection and Cross-lingual Self-Distillation](https://mlsanity.com/paper/2404.08491/) (2024)
- [ADMEDTAGGER: an annotation framework for distillation of expert knowledge for the Polish medical language](https://mlsanity.com/paper/2601.09722/) (2025)

## Abstract (arXiv)

Multilingual pre-trained language models (MPLMs) not only can handle tasks in different languages but also exhibit surprising zero-shot cross-lingual transferability. However, MPLMs usually are not able to achieve comparable supervised performance on rich-resource languages compared to the state-of-the-art monolingual pre-trained models. In this paper, we aim to improve the multilingual model's supervised and zero-shot performance simultaneously only with the resources from supervised languages. Our approach is based on transferring knowledge from high-performance monolingual models with a teacher-student framework. We let the multilingual model learn from multiple monolingual models simultaneously. To exploit the model's cross-lingual transferability, we propose MBLM (multi-branch multilingual language model), a model built on the MPLMs with multiple language branches. Each branch is a stack of transformers. MBLM is trained with the zero-shot-aware training strategy that encourages the model to learn from the mixture of zero-shot representations from all the branches. The results on two cross-lingual classification tasks show that, with only the task's supervised data used, our method improves both the supervised and zero-shot performance of MPLMs.