Test-time adaptation (TTA) is an excellent method which helps generalize models across domains, tasks, and distributions without the use of labeled datasets. Thus, TTA is very useful in natural language processing (NLP) in the dialectal setting, since oftentimes, models are trained on Standard American English (SAE), evaluated on Indian English or Nigerian English, of which distribution differs significantly from the former. This is especially useful since dialectal datasets are scarce. In this paper, we explore one of the most famous TTA techniques, SHOT, in dialectal NLP. We finetune and evaluate SHOT on different combinations of dialectal GLUE. Our findings show that SHOT is a viable technique when labeled datasets are unavailable. We also theoretically propose the concept of dialectal gap and show that it has a positive correlation with the effectiveness of SHOT. We also find that in many cases, finetuning on SAE yields higher performance than finetuning on dialectal data. Our code is available at https://github.com/dukenguyenxyz/dialect-adaptation

翻译：测试时适应（TTA）是一种优秀的方法，它能在不使用标注数据集的情况下，帮助模型跨领域、跨任务、跨分布泛化。因此，TTA在方言场景下的自然语言处理（NLP）中非常有用，因为模型通常在标准美国英语（SAE）上训练，而在印度英语或尼日利亚英语上评估，后者的分布与前者存在显著差异。由于方言数据集稀缺，这一方法尤其具有实用价值。本文探讨了方言NLP中最著名的TTA技术之一——SHOT。我们在不同组合的方言GLUE数据集上对SHOT进行了微调和评估。研究结果表明，在标注数据集不可用时，SHOT是一种可行的技术。我们还从理论上提出了方言间隙的概念，并证明其与SHOT的有效性呈正相关。此外，我们发现许多情况下，在SAE上进行微调比在方言数据上微调能获得更高的性能。我们的代码可在 https://github.com/dukenguyenxyz/dialect-adaptation 获取。