arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2212.09563cs.CL
收藏

面向问答任务的无源域自适应掩码自训练方法

Source-Free Domain Adaptation for Question Answering with Masked Self-training

Western University(西安大略大学);University of California Riverside(加州大学河滨分校)

M. Yin, B. Wang, Y. Dong, C. Ling

AI总结:

针对问答任务无监督域自适应需访问源域数据的限制,提出集成掩码模块的无源自训练方法,通过冻结部分掩码权重保留源域知识、调整其余权重缓解域偏移,在四个基准上性能超越可访问源数据的模型。

摘要:

以往大多数面向问答(QA)的无监督域自适应(UDA)方法在针对目标域微调模型时都需要访问源域数据。然而,源域数据可能包含敏感信息,使用会受到限制。本研究探讨了一种更具挑战性的设置——无源UDA,即我们仅拥有预训练的源模型和目标域数据,无法访问源域数据。我们提出了一种新颖的QA模型自训练方法,该方法集成了一个用于域自适应的独特掩码模块。在源域上训练时,掩码会自动调整以提取关键域知识。为了保留先前学到的域知识,自适应过程中会冻结部分掩码权重,同时调整其他权重,以利用目标域中生成的伪标记样本缓解域偏移。我们在四个基准数据集上的实验结果表明,该方法显著提升了预训练QA模型在目标域上的性能,甚至优于自适应过程中能够访问源数据的模型。

英文摘要:

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.

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。

↑