English

Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching

Computation and Language 2024-06-21 v1 Machine Learning

Abstract

Code-switching is a data augmentation scheme mixing words from multiple languages into source lingual text. It has achieved considerable generalization performance of cross-lingual transfer tasks by aligning cross-lingual contextual word representations. However, uncontrolled and over-replaced code-switching would augment dirty samples to model training. In other words, the excessive code-switching text samples will negatively hurt the models' cross-lingual transferability. To this end, we propose a Progressive Code-Switching (PCS) method to gradually generate moderately difficult code-switching examples for the model to discriminate from easy to hard. The idea is to incorporate progressively the preceding learned multilingual knowledge using easier code-switching data to guide model optimization on succeeding harder code-switching data. Specifically, we first design a difficulty measurer to measure the impact of replacing each word in a sentence based on the word relevance score. Then a code-switcher generates the code-switching data of increasing difficulty via a controllable temperature variable. In addition, a training scheduler decides when to sample harder code-switching data for model training. Experiments show our model achieves state-of-the-art results on three different zero-shot cross-lingual transfer tasks across ten languages.

Keywords

Cite

@article{arxiv.2406.13361,
  title  = {Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching},
  author = {Zhuoran Li and Chunming Hu and Junfan Chen and Zhijun Chen and Xiaohui Guo and Richong Zhang},
  journal= {arXiv preprint arXiv:2406.13361},
  year   = {2024}
}

Comments

9 pages, 5 figures, 6 tables. Accepted by International Joint Conference on Artificial Intelligence (IJCAI 2024)

R2 v1 2026-06-28T17:11:47.203Z