arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.02337cs.CL
收藏

阿塞拜疆语开放基础模型

Open foundation models for Azerbaijani language

The George Washington University(乔治·华盛顿大学);Baku Higher Oil School(巴库高等石油学校);Microsoft(微软公司);New York University(纽约大学)

Jafar Isbarov, Kavsar Huseynova, Elvin Mammadov, Mammad Hajili, Duygu Ataman

AI总结:

本文针对阿塞拜疆语缺乏系统性基准测试的问题,提出了包含大型语料库、编码器模型、标注数据集及全面评估的开源基础模型工作,以推动该语言的开源模型应用。

摘要:

多语言大语言模型的出现使得开发阿塞拜疆语的语言理解与生成系统成为可能。然而,大多数生产级系统依赖云解决方案,如GPT-4。尽管已有若干尝试为阿塞拜疆语开发开放基础模型,但由于缺乏系统性基准测试,这些工作未能得到普遍应用。本文涵盖多项促进阿塞拜疆语开源基础模型的工作。我们引入了(1)一个大型阿塞拜疆语文本语料库,(2)一个在此数据集上训练的仅编码器语言模型系列,(3)用于评估这些模型的标注数据集,以及(4)涵盖所有支持阿塞拜疆语的主要开源模型的广泛评估。

英文摘要:

The emergence of multilingual large language models has enabled the development of language understanding and generation systems in Azerbaijani. However, most of the production-grade systems rely on cloud solutions, such as GPT-4. While there have been several attempts to develop open foundation models for Azerbaijani, these works have not found their way into common use due to a lack of systemic benchmarking. This paper encompasses several lines of work that promote open-source foundation models for Azerbaijani. We introduce (1) a large text corpus for Azerbaijani, (2) a family of encoder-only language models trained on this dataset, (3) labeled datasets for evaluating these models, and (4) extensive evaluation that covers all major open-source models with Azerbaijani support.

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。

↑