重新审视面向低资源语言跨语言命名实体识别的基于投影的数据迁移
Revisiting Projection-based Data Transfer for Cross-Lingual Named Entity Recognition in Low-Resource Languages
AI总结：
本文针对低资源语言跨语言命名实体识别，提出通过回译优化词对齐和形式化投影匹配源实体与目标候选词两项增强，在57种语言上超越现有投影方法，验证了基于投影数据迁移的有效性。
摘要：
跨语言命名实体识别（NER）利用语言间的知识迁移来识别和分类命名实体，使其对低资源语言特别有用。我们表明，基于数据的跨语言迁移方法是跨语言 NER 的有效技术，在低资源语言上能超越多语言语言模型。本文为低资源语言跨语言 NER 的标注投影步骤引入了两项关键增强。首先，我们探索利用回译来优化词对齐以提高准确性。其次，我们提出了一种新颖的形式化投影方法，将源实体与提取的目标候选词进行匹配。通过在涵盖 57 种语言的两个数据集上进行大量实验，我们证明了我们的方法在低资源设置下超越了现有的基于投影的方法。这些发现凸显了基于投影的数据迁移作为低资源语言跨语言命名实体识别中基于模型方法的替代方案的鲁棒性。
英文摘要：
Cross-lingual Named Entity Recognition (NER) leverages knowledge transfer between languages to identify and classify named entities, making it particularly useful for low-resource languages. We show that the data-based cross-lingual transfer method is an effective technique for crosslingual NER and can outperform multilingual language models for low-resource languages. This paper introduces two key enhancements to the annotation projection step in cross-lingual NER for low-resource languages. First, we explore refining word alignments using back-translation to improve accuracy. Second, we present a novel formalized projection approach of matching source entities with extracted target candidates. Through extensive experiments on two datasets spanning 57 languages, we demonstrated that our approach surpasses existing projectionbased methods in low-resource settings. These findings highlight the robustness of projection-based data transfer as an alternative to model-based methods for crosslingual named entity recognition in lowresource 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。
