Domain generalization is hitherto an underexplored area applied in abstractive summarization. Moreover, most existing works on domain generalization have sophisticated training algorithms. In this paper, we propose a lightweight, weight averaging based, Domain Aligned Prefix Averaging approach to domain generalization for abstractive summarization. Given a number of source domains, our method first trains a prefix for each one of them. These source prefixes generate summaries for a small number of target domain documents. The similarity of the generated summaries to their corresponding documents is used for calculating weights required to average source prefixes. In DAPA, prefix tuning allows for lightweight finetuning, and weight averaging allows for the computationally efficient addition of new source domains. When evaluated on four diverse summarization domains, DAPA shows comparable or better performance against the baselines, demonstrating the effectiveness of its prefix averaging scheme.

翻译：领域泛化迄今为止在抽象式摘要领域中仍是一个探索不足的研究方向。此外，现有大多数领域泛化工作都采用复杂的训练算法。本文提出一种轻量级、基于权重平均的领域对齐前缀平均方法，用于抽象式摘要中的领域泛化。给定若干源领域，我们的方法首先为每个源领域训练一个前缀。这些源前缀为目标领域中的少量文档生成摘要。生成的摘要与其对应文档之间的相似度被用于计算平均源前缀所需的权重。在DAPA方法中，前缀调优实现了轻量级微调，而权重平均则允许以计算高效的方式添加新的源领域。在四个不同的摘要领域上进行评估时，DAPA表现出与基线方法相当或更优的性能，证明了其前缀平均方案的有效性。