Research on Optimization of Knowledge Graph Construction Flow Chart

Li, Fengru; Xie, Wei; Wang, Xiaowei; Fan, Zhe

doi:10.1109/itaic49862.2020.9338900

Cited by 4 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Either way, creating a knowledge graph becomes especially difficult when working with large amounts (Fensel et al 2020) of differently structured data from various sources (Tamašauskaitė and Groth 2023). Many approaches have been proposed for creating knowledge graphs, including bottom-up (Li et al 2020), top-down (Li et al 2020) and in-between methods (Ji et al 2022;Tamašauskaitė and Groth 2023). The procedures generally consist of multiple steps that deal with data extraction, knowledge fusion and information representation.…”

Section: Related Work and Research Objectivementioning

confidence: 99%

“…The reliance on human expertise constitutes a major impediment to the process. This is due to the sheer amount of data (Li et al 2020;Tamašauskaitė and Groth 2023), which makes manual knowledge graph creation labour-intensive (Ruan et al 2016), expensive (Ji et al 2022) and prone to human errors (Kejriwal 2019). At the same time, there is a shortage of relevant experts in many domains (Abu-Salih 2021).…”

Section: Related Work and Research Objectivementioning

confidence: 99%

“…Instead, in many instances, domainspecific knowledge graphs have been built using more traditional methodologies (Dong, Yu, and Li 2021;Ruan et al 2016;Song et al 2019). In addition, numerous existing studies have focused on open data sets (e.g., Wikidata) based on information generally available on the internet (Chaudhri et al 2022;Google 2023;Li et al 2020;schema.org 2022).…”

Section: Related Work and Research Objectivementioning

confidence: 99%

“…Once the domain and scope of the knowledge engineering endeavor have been defined, the interviewees propagate a model-first approach when it comes to enterprise knowledge graph creation. This top-down approach -where a (visual) ontology schema is built as one of the first steps -is also outlined by Li et al (2020) and Tamašauskaitė and Groth (2023). When no existing ontology can be reused, a new one needs to be constructed.…”

Section: An Enterprise Knowledge Graph Engineering Processmentioning

confidence: 99%

“…In the literature (Ji et al 2022;Li et al 2020;Tamašauskaitė and Groth 2023), knowledge extraction is described as the extraction of entities, attributes and relationships from data sources. As soon as the required data sources are identified, knowledge can be extracted from them according to the previously constructed ontology schema.…”

Section: An Enterprise Knowledge Graph Engineering Processmentioning

confidence: 99%

See 4 more Smart Citations

An LLM-Aided Enterprise Knowledge Graph (EKG) Engineering Process

Laurenzi,

Mathys,

Martin

2024

AAAI-SS

View full text Add to dashboard Cite

Conventional knowledge engineering approaches aiming to create Enterprise Knowledge Graphs (EKG) still require a high level of manual effort and high ontology expertise, which hinder their adoption across industries. To tackle this issue, we explored the use of Large Language Models (LLMs) for the creation of EKGs through the lens of a design-science approach. Findings from the literature and from expert interviews led to the creation of the proposed artefact, which takes the form of a six-step process for EKG development. Scenarios on how to use LLMs are proposed and implemented for each of the six steps. The process is then evaluated with an anonymised data set from a large Swiss company. Results demonstrate that LLMs can support the creation of EKGs, offering themselves as a new aid for knowledge engineers.

show abstract

Section: Related Work and Research Objectivementioning

confidence: 99%

Section: Related Work and Research Objectivementioning

confidence: 99%

Section: Related Work and Research Objectivementioning

confidence: 99%

Section: An Enterprise Knowledge Graph Engineering Processmentioning

confidence: 99%

Section: An Enterprise Knowledge Graph Engineering Processmentioning

confidence: 99%

See 3 more Smart Citations

An LLM-Aided Enterprise Knowledge Graph (EKG) Engineering Process

Laurenzi,

Mathys,

Martin

2024

AAAI-SS

View full text Add to dashboard Cite

show abstract

Attribute expansion relation extraction approach for smart engineering decision‐making in edge environments

Cui,

Zhang,

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryIn sedimentology, the integration of intelligent engineering decision‐making with edge computing environments aims to furnish engineers and decision‐makers with precise, real‐time insights into sediment‐related issues. This approach markedly reduces data transfer time and response latency by harnessing the computational power of edge computing, thereby bolstering the decision‐making process. Concurrently, the establishment of a sediment knowledge graph serves as a pivotal conduit for disseminating sediment‐related knowledge in the realm of intelligent engineering decision‐making. Moreover, it facilitates a comprehensive exploration of the intricate evolutionary and transformative processes inherent in sediment materials. By unveiling the evolutionary trajectory of life on Earth, the sediment knowledge graph catalyzes a deeper understanding of our planet's history and dynamics. Relationship extraction, as a key step in knowledge graph construction, implements automatic extraction and establishment of associations between entities from a large amount of sedimentary literature data. However, sedimentological literature presents multi‐source heterogeneous features, which leads to a weak representation of hidden relationships, thus decreasing the accuracy of relationship extraction. In this article, we propose an attribute‐extended relation extraction approach (AERE), which is specifically designed for sedimentary relation extraction scenarios. First, context statements containing sediment entities are obtained from the literature. Then, a cohesive hierarchical clustering algorithm is used to extend the relationship attributes between sediments. Finally, mine the relationships between entities based on AERE. The experimental results show that the proposed model can effectively extract the hidden relations and exhibits strong robustness in dealing with redundant noise before and after sentences, which in turn improves the completeness of the relations between deposits. After the relationship extraction, a proprietary sediment knowledge graph is constructed with the extracted triads.

show abstract