Data for Progress on Climate Action: a Multilingual Machine Learning Analysis of the Global Stocktake

Data to go with our submission to Climatic Change titled "Progress on Climate Action: a Multilingual Machine Learning Analysis of the Global Stocktake". Dataset contains the embeddings (.zip with pickles) as well as the associated document items (idem), the most-closely associated keywords and paragraphs per topic in the final model (.xlsx), the reduced 2d embeddings with all selected paragraphs (.csv utf-8 encoded), as well as an overview with the meta-data per source (.csv utf-8 encoded).本数据集为我们提交至学术期刊《气候变化》(Climatic Change)的论文《气候行动进展：全球盘点(Global Stocktake)的多语言机器学习分析》的配套数据。数据集包含以下内容：嵌入向量文件（内含pickle序列化文件的ZIP压缩包）、配套文档条目（格式与上述嵌入向量文件一致）、最终模型中各主题对应的最相关关键词与段落（.xlsx格式）、包含所有选定段落的降维二维嵌入向量（UTF-8编码的.csv格式），以及各来源元数据概览（UTF-8编码的.csv格式）。