aisingapore/Linguistic-Diagnostics-Syntax
收藏Hugging Face2024-12-20 更新2025-05-31 收录
下载链接：
https://hf-mirror.com/datasets/aisingapore/Linguistic-Diagnostics-Syntax
下载链接
链接失效反馈官方服务：
资源简介：
LINDSEA Syntax是一个印尼语语法诊断数据集，用于评估大型语言模型对印尼语的语法理解能力。它包含id（印尼语）的语言分割和fewshot示例分割，数据集的特征包括示例ID、标签、提示、提示模板和元数据等。元数据中包含了语言、语言学现象、类别、子类别等详细信息。数据集分为id和id_fewshot两个部分，分别有380个和5个示例。
LINDSEA Syntax is an Indonesian syntax diagnostic dataset designed to evaluate large language models understanding of Indonesian grammar. It includes an Indonesian (id) language split and fewshot example splits. The dataset features include example ID, label, prompts, prompt templates, and metadata, which contain details such as language, linguistic phenomena, category, subcategory, etc. The dataset is divided into two parts, id and id_fewshot, with 380 and 5 examples respectively.
提供机构：
aisingapore
