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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zhuoran, Hu, Chunming, Chen, Junfan, Chen, Zhijun, Guo, Xiaohui, Zhang, Richong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916295294844928
author Li, Zhuoran
Hu, Chunming
Chen, Junfan
Chen, Zhijun
Guo, Xiaohui
Zhang, Richong
author_facet Li, Zhuoran
Hu, Chunming
Chen, Junfan
Chen, Zhijun
Guo, Xiaohui
Zhang, Richong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13361
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching
Li, Zhuoran
Hu, Chunming
Chen, Junfan
Chen, Zhijun
Guo, Xiaohui
Zhang, Richong
Computation and Language
Machine Learning
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.
title Improving Zero-Shot Cross-Lingual Transfer via Progressive Code-Switching
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2406.13361