arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.08020cs.AIcs.CLcs.DLcs.IRcs.LG
收藏

使用神经Transformer增强知识图谱层级结构

Augmenting Knowledge Graph Hierarchies Using Neural Transformers

Adobe Inc.(奥多比公司)

Sanat Sharma, Mayank Poddar, Jayant Kumar, Kosta Blank, Tracy King

AI总结:

本研究针对知识图谱层级增强问题,利用大语言模型结合少样本提示、单样本生成及循环生成技术,实现小型领域KG层级的有效增强,大幅提升了意图与颜色类别的层级覆盖率。

摘要:

知识图谱是用于组织、推荐和分类数据的实用工具。知识图谱中的层级结构对提升图谱内数据的理解度与分类度有显著作用。本研究利用大语言模型生成并增强现有知识图谱的层级结构。对于节点数少于10万的小型领域特定知识图谱(KG),我们发现少样本提示与单样本生成相结合的方式效果良好,而更大规模的知识图谱可能需要循环生成。我们提出了多种层级增强技术,在我们的知识图谱中,这些技术使意图类别的层级覆盖率提升了98%,颜色类别的覆盖率提升了99%。

英文摘要:

Knowledge graphs are useful tools to organize, recommend and sort data. Hierarchies in knowledge graphs provide significant benefit in improving understanding and compartmentalization of the data within a knowledge graph. This work leverages large language models to generate and augment hierarchies in an existing knowledge graph. For small (<100,000 node) domain-specific KGs, we find that a combination of few-shot prompting with one-shot generation works well, while larger KG may require cyclical generation. We present techniques for augmenting hierarchies, which led to coverage increase by 98% for intents and 99% for colors in our knowledge graph.

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。

↑