陈俊帆
点赞：
陈俊帆
点赞：
论文
Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching
发布时间：2025-10-22点击次数：
发表刊物：
Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI), CCF-A
摘要：
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 that our model achieves state-of-the-art results on three different zero-shot cross-lingual transfer tasks across ten languages.
合写作者：
Zhuoran Li,胡春明,陈俊帆, Zhijun Chen, Xiaohui Guo,张日崇
论文类型：
国际学术会议
页面范围：
6388-6396
是否译文：
否
发表时间：
2024-01-01