文件列表:
G2T:基于预训练语言模型和社区检测的主题建模简单通用框架【英文版】.pdf |
下载文档 |
资源简介
>
英文标题:G2T: A simple but versatile framework for topic modeling based on pretrained language model and community detection中文摘要:本文提出了一种名为图向话题(G2T)的框架,该框架能够使用预训练语言模型获取文档表示,并通过语义图和社区检测等方法进行主题建模。自动评估结果表明,G2T 在英文和中文文档上均取得了最优表现,并且比基线模型产生了更好的可解释性和覆盖范围。英文摘要:It has been reported that clustering-based topic models, which clusterhigh-quality sentence embeddings with an appropriate word selection method, cangenerate better topics than generative probabilistic topic models. However,these approaches suffer fro
加载中...
已阅读到文档的结尾了