arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.03284cs.AIcs.CLcs.IR
收藏

iText2KG:利用大语言模型进行增量式知识图谱构建

iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

INSA Lyon(里昂国立应用科学学院);CNRS(法国国家科学研究中心);Universite Claude Bernard Lyon 1(里昂第一大学(克洛德·贝尔纳));GAUC;AUVALIE

Yassir Lairgi, Ludovic Moncla, Rémy Cazabet, Khalid Benabdeslem, Pierre Cléau

AI总结:

本文提出 iText2KG,一种基于大语言模型的零样本、增量式、主题无关知识图谱构建方法,通过四个模块实现无后处理构建,并在论文、网站和简历转图谱任务中优于基线方法。

摘要:

大多数可用数据是非结构化的,这使得获取有价值的信息变得困难。自动构建知识图谱(KGs)对于结构化数据并使其可访问至关重要,它使用户能够有效地搜索信息。知识图谱还有助于洞察、推理和推断。传统的自然语言处理方法,如命名实体识别和关系抽取,是信息检索中的关键技术,但面临一些局限性,包括使用预定义实体类型以及需要监督学习。当前的研究利用大语言模型的能力,例如零样本或少样本学习。然而,未解决且在语义上重复的实体和关系仍然带来挑战,导致图谱不一致,并需要大量的后处理。此外,大多数方法依赖于特定主题。在本文中,我们提出了 iText2KG,一种无需后处理、增量式且与主题无关的知识图谱构建方法。这种即插即用、零样本的方法适用于广泛的知识图谱构建场景,包含四个模块:文档蒸馏器(Document Distiller)、增量式实体抽取器(Incremental Entity Extractor)、增量式关系抽取器(Incremental Relation Extractor)以及图谱集成与可视化器(Graph Integrator and Visualization)。我们的方法在三种场景下相较于基线方法展示了更优越的性能:将科学论文转换为图谱、将网站转换为图谱以及将简历转换为图谱。

英文摘要:

Most available data is unstructured, making it challenging to access valuable information. Automatically building Knowledge Graphs (KGs) is crucial for structuring data and making it accessible, allowing users to search for information effectively. KGs also facilitate insights, inference, and reasoning. Traditional NLP methods, such as named entity recognition and relation extraction, are key in information retrieval but face limitations, including the use of predefined entity types and the need for supervised learning. Current research leverages large language models' capabilities, such as zero- or few-shot learning. However, unresolved and semantically duplicated entities and relations still pose challenges, leading to inconsistent graphs and requiring extensive post-processing. Additionally, most approaches are topic-dependent. In this paper, we propose iText2KG, a method for incremental, topic-independent KG construction without post-processing. This plug-and-play, zero-shot method is applicable across a wide range of KG construction scenarios and comprises four modules: Document Distiller, Incremental Entity Extractor, Incremental Relation Extractor, and Graph Integrator and Visualization. Our method demonstrates superior performance compared to baseline methods across three scenarios: converting scientific papers to graphs, websites to graphs, and CVs to graphs.

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。

↑