当分布偏移时:面向低资源语言的因果泛化
When Distributions Shifts: Causal Generalization for Low-Resource Languages
AI总结:
本研究针对低资源语言,通过因果数据增强和不变因果表示学习提升领域泛化能力,实验显示在多语言任务中提升了模型鲁棒性和分布外性能。
摘要:
机器学习模型在面对分布偏移时常常失效,这种问题在低资源环境下尤为严重,因为有限的数据限制了鲁棒的泛化能力。领域泛化(DG)方法通过学习在不同领域中保持不变的表示来解决这一挑战,通常利用因果原理。在本工作中,我们研究了两种针对低资源自然语言处理的因果领域泛化方法。首先,我们利用GPT-4o-mini进行因果数据增强,生成反事实改写,用于尼日利亚语和伊博语的情感分类任务,基于NaijaSenti推特语料库。其次,我们研究了使用去偏见的方面评论(DINER)框架进行基于方面的情感分析的不变因果表示学习。我们通过引入Afri-SemEval数据集扩展了DINER到多语言环境,该数据集包含17种语言,均源自SemEval-2014任务的翻译。实验表明,模型在面对未见领域时表现出改进的鲁棒性,反事实增强和因果表示学习在多个语言中均提升了分布外性能。
英文摘要:
Machine learning models often fail under distribution shifts, a problem exacerbated in low-resource settings where limited data restricts robust generalization. Domain generalization(DG) methods address this challenge by learning representations that remain invariant across domains, frequently leveraging causal principles. In this work, we study two causal DG approaches for low-resource natural language processing. First, we apply causal data augmentation using GPT-4o-mini to generate counterfactual paraphrases for sentiment classification on the NaijaSenti Twitter corpus in Yoruba and Igbo. Second, we investigate invariant causal representation learning with the Debiasing in Aspect Review (DINER) framework for aspect-based sentiment analysis. We extend DINER to a multilingual setting by introducing Afri-SemEval, a dataset of 17 languages translated from SemEval-2014 Task. Experiments show improved robustness to unseen domains, with consistent gains from counterfactual augmentation and enhanced out-of-distribution performance from causal representation learning across multiple languages.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。