arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.14908cs.IRcs.CEcs.CL
收藏

Triplètoile:从微博客文本中提取知识

Triplètoile: Extraction of Knowledge from Microblogging Text

University of Cagliari(卡利亚里大学);European Commission, Joint Research Centre (DG JRC)(欧洲委员会联合研究中心);Laboratoire d’Informatique de Paris Nord, Sorbonne Paris Nord University(巴黎北信息学实验室,巴黎北索邦大学);GESIS Leibniz Institute for the Social Sciences(莱布尼茨社会科学研究所(GESIS));Knowledge Media Institute, The Open University(开放大学知识媒体研究所);University of Milano Bicocca(米兰比可卡大学)

Vanni Zavarella, Sergio Consoli, Diego Reforgiato Recupero, Gianni Fenu, Simone Angioni, Davide Buscaldi, Danilo Dessì, Francesco Osborne

AI总结:

本文提出一种增强的信息提取流程,利用依存句法分析和词嵌入层次聚类进行无监督关系分类,从社交媒体微博客帖子中提取开放域实体知识图谱,精确度超95%且优于类似流程。

摘要:

近年来出现了许多从科学出版物和专利等文档中自动提取知识图谱的方法和流程。然而,将这些方法适配以纳入微博客帖子和新闻等替代文本源已被证明具有挑战性,因为它们难以对这些来源中常见的开放域实体和关系进行建模。在本文中,我们提出了一种增强的信息提取流程,专为从社交媒体平台上的微博客帖子中提取包含开放域实体的知识图谱而定制。该流程利用依存句法分析,并通过对词嵌入进行层次聚类,以无监督方式对实体关系进行分类。我们提供了一个用例,从包含10万条关于数字化转型的推文语料库中提取语义三元组,并公开发布了生成的知识图谱。在同一数据集上,我们进行了两项实验评估,结果表明该系统生成的三元组精确度超过95%,并且在精确度上比类似流程高出约5%,同时生成了数量相对更多的三元组。

英文摘要:

Numerous methods and pipelines have recently emerged for the automatic extraction of knowledge graphs from documents such as scientific publications and patents. However, adapting these methods to incorporate alternative text sources like micro-blogging posts and news has proven challenging as they struggle to model open-domain entities and relations, typically found in these sources. In this paper, we propose an enhanced information extraction pipeline tailored to the extraction of a knowledge graph comprising open-domain entities from micro-blogging posts on social media platforms. Our pipeline leverages dependency parsing and classifies entity relations in an unsupervised manner through hierarchical clustering over word embeddings. We provide a use case on extracting semantic triples from a corpus of 100 thousand tweets about digital transformation and publicly release the generated knowledge graph. On the same dataset, we conduct two experimental evaluations, showing that the system produces triples with precision over 95% and outperforms similar pipelines of around 5% in terms of precision, while generating a comparatively higher number of triples.

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。

↑