Most previous unsupervised domain adaptation (UDA) methods for question answering(QA) require access to source domain data while fine-tuning the model for the target domain. Source domain data may, however, contain sensitive information and may be restricted. In this study, we investigate a more challenging setting, source-free UDA, in which we have only the pretrained source model and target domain data, without access to source domain data. We propose a novel self-training approach to QA models that integrates a unique mask module for domain adaptation. The mask is auto-adjusted to extract key domain knowledge while trained on the source domain. To maintain previously learned domain knowledge, certain mask weights are frozen during adaptation, while other weights are adjusted to mitigate domain shifts with pseudo-labeled samples generated in the target domain. %As part of the self-training process, we generate pseudo-labeled samples in the target domain based on models trained in the source domain. Our empirical results on four benchmark datasets suggest that our approach significantly enhances the performance of pretrained QA models on the target domain, and even outperforms models that have access to the source data during adaptation.

翻译：大多数先前的无监督域适应方法在针对目标域微调问答模型时，需要访问源域数据。然而源域数据可能包含敏感信息而受到限制。本研究探讨了更具挑战性的场景——源域缺失的无监督域适应，即仅拥有预训练源模型与目标域数据，无法获取源域数据。我们提出了一种新颖的问答模型自训练方法，该方法集成了专用于域适应的掩码模块。该掩码在源域训练过程中自动调整以提取关键域知识。为保持先前习得的域知识，适应过程中部分掩码权重被冻结，其他权重则通过基于目标域生成的伪标签样本进行调整以缓解域偏移。在四个基准数据集上的实验结果表明，我们的方法显著提升了预训练问答模型在目标域的性能，甚至超越了适应过程中可访问源域数据的模型。