# Bridging the domain gap in cross-lingual document classification

arXiv: https://arxiv.org/abs/1909.07009 · HTML: https://mlsanity.com/paper/1909.07009/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 8 of 8)

- [pNLP-Mixer: an Efficient all-MLP Architecture for Language](https://mlsanity.com/paper/2202.04350/) (2022)
- [Multilingual and cross-lingual document classification: A meta-learning approach](https://mlsanity.com/paper/2101.11302/) (2021)
- [Lex Rosetta: Transfer of Predictive Models Across Languages, Jurisdictions, and Legal Domains](https://mlsanity.com/paper/2112.07882/) (2021)
- [Lessons learned from the evaluation of Spanish Language Models](https://mlsanity.com/paper/2212.08390/) (2022)
- [On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?](https://mlsanity.com/paper/2406.14267/) (2024)
- [Meta-XNLG: A Meta-Learning Approach Based on Language Clustering for Zero-Shot Cross-Lingual Transfer and Generation](https://mlsanity.com/paper/2203.10250/) (2022)
- [A Multilingual Bag-of-Entities Model for Zero-Shot Cross-Lingual Text Classification](https://mlsanity.com/paper/2110.07792/) (2021)
- [Lorenz System State Stability Identification using Neural Networks](https://mlsanity.com/paper/2106.08489/) (2021)

## Abstract (arXiv)

The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language barrier using language universal representations. However, even if the language problem was resolved, models trained in one language would not transfer to another language perfectly due to the natural domain drift across languages and cultures. We consider the setting of semi-supervised cross-lingual understanding, where labeled data is available in a source language (English), but only unlabeled data is available in the target language. We combine state-of-the-art cross-lingual methods with recently proposed methods for weakly supervised learning such as unsupervised pre-training and unsupervised data augmentation to simultaneously close both the language gap and the domain gap in XLU. We show that addressing the domain gap is crucial. We improve over strong baselines and achieve a new state-of-the-art for cross-lingual document classification.