[论文] SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation

论文概要

研究领域: NLP 作者: Marek Šuppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková, Viktória Ondrejová 发布时间: 2026-06-11 arXiv: 2606.13647

中文摘要

我们引入SkMTEB，首个面向斯洛伐克语的MTEB风格全面文本嵌入基准，包含7个任务类型的31个数据集。我们通过对多语言E5模型应用词汇裁剪和微调开发e5-sk-small（45M）和e5-sk-large（365M）。尽管尺寸缩减高达62%，我们的模型仍与专有API保持竞争力且可本地部署。

原文摘要

We introduce SkMTEB, the first comprehensive MTEB-style text embedding benchmark for Slovak, comprising 31 datasets across 7 task types. We develop e5-sk-small (45M) and e5-sk-large (365M) by applying vocabulary trimming and fine-tuning to Multilingual E5 models. Despite size reductions up to 62%, our models achieve competitive performance with proprietary APIs while remaining locally deployable.

--- *自动采集于 2026-06-14*

#论文 #arXiv #NLP #小凯