ZGUL：使用语言适配器的多源集成实现向未见语言的零样本泛化
ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters
AI总结：
本文提出一种名为ZGUL的新型神经架构，通过在训练和测试时集成多个相关源语言的语言适配器，有效解决了向未见语言的零样本跨语言迁移问题，并在POS标注和NER任务上取得了优于基线的显著效果。
摘要：
我们通过使用语言适配器（LAs）来解决NLP任务中的零样本跨语言迁移问题。早期的大多数工作探索了使用单一源语言（通常是英语）的适配器进行训练，并使用目标LA或另一种相关语言的LA进行测试。训练目标LA需要无标签数据，这对于低资源未见语言可能不易获得：这些语言既未被底层多语言语言模型（例如mBERT）见过，我们也没有它们的任何（有标签或无标签）数据。我们认为，为了实现更有效的跨语言迁移，不仅需要单一源LA，还需要在训练和测试时利用多个（在语言学或地理上相关的）源语言的LA——我们通过新颖的神经架构ZGUL对此进行了研究。在涵盖15种未见目标语言的四个语言群体中进行的广泛实验表明，在POS标注和NER任务上，平均F1分数比标准微调和其他强基线提高了多达3.2分。我们还将ZGUL扩展到目标语言具有（1）一些无标签数据或（2）少样本训练示例的设置中。我们发现ZGUL在这些设置中也继续优于基线。
英文摘要：
We tackle the problem of zero-shot cross-lingual transfer in NLP tasks via the use of language adapters (LAs). Most of the earlier works have explored training with adapter of a single source (often English), and testing either using the target LA or LA of another related language. Training target LA requires unlabeled data, which may not be readily available for low resource unseen languages: those that are neither seen by the underlying multilingual language model (e.g., mBERT), nor do we have any (labeled or unlabeled) data for them. We posit that for more effective cross-lingual transfer, instead of just one source LA, we need to leverage LAs of multiple (linguistically or geographically related) source languages, both at train and test-time - which we investigate via our novel neural architecture, ZGUL. Extensive experimentation across four language groups, covering 15 unseen target languages, demonstrates improvements of up to 3.2 average F1 points over standard fine-tuning and other strong baselines on POS tagging and NER tasks. We also extend ZGUL to settings where either (1) some unlabeled data or (2) few-shot training examples are available for the target language. We find that ZGUL continues to outperform baselines in these settings too.
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。
