低资源适配器是正则化器，而非语言学家
Limited-Resource Adapters Are Regularizers, Not Linguists
AI总结：
本研究探究适配器融合与交叉注意力微调以提升三种低资源克里奥尔语的机器翻译性能，发现适配器的作用主要是参数正则化而非语言信息迁移。
摘要：
从相关高资源语言进行跨语言迁移是增强低资源语言技术的成熟策略。先前工作表明，适配器在改进低资源机器翻译（MT）等方面展现出潜力。在本研究中，我们探究了一种适配器融合方法，结合预训练MT模型的交叉注意力微调，以利用语言迁移处理三种低资源克里奥尔语，这些语言在不同语言维度上与不同语群表现出相关性。我们的方法显著优于基线性能。然而，我们发现语言相关性——甚至其缺失——与适配器性能并无显著协变关系。令人惊讶的是，我们的交叉注意力微调方法在使用随机初始化的适配器时同样有效，这意味着在此设置下，适配器的益处在于参数正则化，而非有意义的信息迁移。我们提供了支持这一正则化假设的分析。我们的发现强调了神经语言处理涉及诸多成功因素，且并非所有神经方法都以直观方式利用语言知识。
英文摘要：
Cross-lingual transfer from related high-resource languages is a well-established strategy to enhance low-resource language technologies. Prior work has shown that adapters show promise for, e.g., improving low-resource machine translation (MT). In this work, we investigate an adapter souping method combined with cross-attention fine-tuning of a pre-trained MT model to leverage language transfer for three low-resource Creole languages, which exhibit relatedness to different language groups across distinct linguistic dimensions. Our approach improves performance substantially over baselines. However, we find that linguistic relatedness -- or even a lack thereof -- does not covary meaningfully with adapter performance. Surprisingly, our cross-attention fine-tuning approach appears equally effective with randomly initialized adapters, implying that the benefit of adapters in this setting lies in parameter regularization, and not in meaningful information transfer. We provide analysis supporting this regularization hypothesis. Our findings underscore the reality that neural language processing involves many success factors, and that not all neural methods leverage linguistic knowledge in intuitive ways.
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。
