分析低资源非洲语言命名实体识别中的跨语言迁移
Analysing Cross-Lingual Transfer in Low-Resourced African Named Entity Recognition
AI总结：
本文从命名实体识别角度研究了十种低资源非洲语言间的跨语言迁移特性，发现自适应微调与迁移语言选择影响零样本迁移性能，且数据重叠量比语言地理或谱系距离更能预测迁移效果。
摘要：
迁移学习使得几乎所有NLP任务的性能大幅提升，同时让下游模型更易训练且训练更快。这一方法也被扩展至低资源语言，并取得了一定成功。我们从命名实体识别任务的角度，研究了十种低资源语言之间的跨语言迁移学习特性。我们具体考察了自适应微调的程度和迁移语言的选择如何影响零样本迁移性能。我们发现，在单一语言上表现良好的模型往往以牺牲对其他语言的泛化能力为代价，而对其他语言具有最佳泛化能力的模型在单一语言性能上则表现不佳。此外，源数据集与目标数据集之间的数据重叠量是比语言间的地理距离或谱系距离更好的迁移性能预测指标。
英文摘要：
Transfer learning has led to large gains in performance for nearly all NLP tasks while making downstream models easier and faster to train. This has also been extended to low-resourced languages, with some success. We investigate the properties of cross-lingual transfer learning between ten low-resourced languages, from the perspective of a named entity recognition task. We specifically investigate how much adaptive fine-tuning and the choice of transfer language affect zero-shot transfer performance. We find that models that perform well on a single language often do so at the expense of generalising to others, while models with the best generalisation to other languages suffer in individual language performance. Furthermore, the amount of data overlap between the source and target datasets is a better predictor of transfer performance than either the geographical or genetic distance between the languages.
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。
