Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling. This leads to good in-domain scores but can be impractical for domain- or resource-restricted settings. A solution is to use a related-domain adapter for the novel domain at test time. In this paper, we introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains. Our approach is embarrassingly parallel: first, we train a set of domain-specific adapters; then, for each novel domain, we determine which adapters should be averaged at test time. We present extensive experiments showing that AdapterSoup consistently improves performance to new domains without extra training. We also explore weight averaging of adapters trained on the same domain with different hyper-parameters, and show that it preserves the performance of a PLM on new domains while obtaining strong in-domain results. We explore various approaches for choosing which adapters to combine, such as text clustering and semantic similarity. We find that using clustering leads to the most competitive results on novel domains.

翻译：预训练语言模型（PLMs）在大规模语料库上训练，但通常需要针对特定领域进行专门化。一种参数高效的适配方法建议为每个领域训练一个语言建模任务适配器。这能取得良好的领域内评分，但在领域或资源受限场景下可能不切实际。一种解决方法是在测试时对新型领域使用相关领域适配器。本文提出AdapterSoup，该方法对不同领域训练的适配器进行权重空间平均。我们的方法具有高度并行性：首先训练一组领域特定适配器，然后在测试时针对每个新型领域确定应平均哪些适配器。通过大量实验证明，AdapterSoup无需额外训练即可持续提升在新领域的性能。我们还探索了对相同领域但不同超参数训练的适配器进行权重平均，结果表明该方法在保持预训练语言模型在新领域性能的同时，能获得强劲的领域内结果。我们研究了文本聚类和语义相似度等多种适配器组合选择方法，发现使用聚类能在新型领域取得最具竞争力的结果。