Towards Knowledge Graphs Validation Through Weighted Knowledge Sources

Huaman, Elwin; Tauqeer, Amar; Fensel, Dieter

doi:10.1007/978-3-030-91305-2_4

Cited by 8 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anyway, a knowledge graph is indeed by definition incomplete, i.e., it is not able to capture the entire knowledge on the system, but it can be progressively revised to this extent. Further discussion should consider different possibilities for its validation (Huaman, Tauqeer, and Fensel 2021).…”

Section: Discussionmentioning

confidence: 99%

Extending Safety Control Structures: A Knowledge Graph for STAMP

Simone,

Akel,

Alvino

et al. 2023

Proceeding of the 33rd European Safety and Reliability Conference

View full text Add to dashboard Cite

The increasing interactions among technical components and human agents in modern industrial systems poses new challenges for safety management, demanding for novel approaches to extend techno-centric investigations with social-oriented analyses. In these scenarios, it becomes crucial the usage of a detailed accident analysis beyond immediate failures, to encompass physical, cyber and social aspects. The Systems-Theoretic Accident Model and Processes (STAMP) was developed as an accident model that makes use of systems theory to arrange a causality model focusing on system hazards. The inner nature of a STAMP model, which maps connections (feedbacks and control actions) among system elements, matches the principles of a graph representation, which are made up of vertices and edges mapping connections. This correspondence may then enable the exploitation of a STAMP-driven graph to guide safety assessments by systematic graph analyses. This paper explores the possibility of deriving a knowledge graph from a STAMP safety control structure and use it as a key element for subsequent hazard analyses. The study is instantiated on case study related to the inspection (based upon Seveso III directive) of a Seveso establishment. The analysis is meant to highlight the safety requirements to adapt the inspection procedure to possible future changes, as promoted by an energy transition. The preliminary results show the potential of such tools to empower -or possibly update -modern Safety Management System.

show abstract

Section: Discussionmentioning

confidence: 99%

Extending Safety Control Structures: A Knowledge Graph for STAMP

Simone,

Akel,

Alvino

et al. 2023

Proceeding of the 33rd European Safety and Reliability Conference

View full text Add to dashboard Cite

show abstract

“…Additionally, some limitations for semantic search engines are: the knowledge acquisition process limits the powerfulness of semantic search engines [50], and furthermore, there is some work to be done on matching and ranking methods used on semantic search engines, which mostly reuse information retrieval techniques [16]. Last but not least, search engines must rely on high-quality knowledge sources [51]. However, it is not clear to which degree knowledge sources are correct or complete, e.g., Google's search engine relies on Wikidata, which might contain errors, duplicates, or missing values.…”

Section: Current State Of the Art And Related Workmentioning

confidence: 99%

Interactive Search on the Web: The Story So Far

et al. 2022

Self Cite

View full text Add to dashboard Cite

Search on the web, specifically fetching of the relevant content, has been paid attention to since the advent of the web and particularly in recent years due to the tremendous growth in the volume of data and web pages. This paper categorizes the search services from the early days of the web to the present into keyword search engines, semantic search engines, question answering systems, dialogue systems and chatbots. As the first generation of search engines, keyword search engines have adopted keyword-based techniques to find the web pages containing the query keywords and ranking search results. In contrast, semantic search engines try to find meaningful and accurate results on the meaning and relations of things. Question-answering systems aim to find precise answers to natural language questions rather than returning a ranked list of relevant sources. As a subset of question answering systems, dialogue systems target to interact with human users through a dialog expressed in natural language. As a subset of dialogue systems, chatbots try to simulate human-like conversations. The paper provides an overview of the typical aspects of the studied search services, including process models, data preparation and presentation, common methodologies and categories.

show abstract

“…In the literature, the vast majority of studies concerned with the evaluation of KGs have focused on intrinsic metrics that are working exclusively with the triples of a graph. Several works introduce quality metrics like accuracy, consistency, or trustworthiness and propose ways to determine them quantitatively [4,8,16,33,35]. Färber et al [7] and Heist et al [11] compare KGs with respect to size, complexity, coverage, and overlap.…”

Section: Introduction 1motivationmentioning

confidence: 99%

DBkWik++- Multi Source Matching of Knowledge Graphs

Hertling

Paulheim

2022

Knowledge Graphs and Semantic Web

View full text Add to dashboard Cite

In recent years, countless research papers have addressed the topics of knowledge graph creation, extension, or completion in order to create knowledge graphs that are larger, more correct, or more diverse. This research is typically motivated by the argumentation that using such enhanced knowledge graphs to solve downstream tasks will improve performance. Nonetheless, this is hardly ever evaluated. Instead, the predominant evaluation metrics -aiming at correctness and completeness -are undoubtedly valuable but fail to capture the complete picture, i.e., how useful the created or enhanced knowledge graph actually is. Further, the accessibility of such a knowledge graph is rarely considered (e.g., whether it contains expressive labels, descriptions, and sufficient context information to link textual mentions to the entities of the knowledge graph). To better judge how well knowledge graphs perform on actual tasks, we present KGrEaT -a framework to estimate the quality of knowledge graphs via actual downstream tasks like classification, clustering, or recommendation. Instead of comparing different methods of processing knowledge graphs with respect to a single task, the purpose of KGrEaT is to compare various knowledge graphs as such by evaluating them on a fixed task setup. The framework takes a knowledge graph as input, automatically maps it to the datasets to be evaluated on, and computes performance metrics for the defined tasks. It is built in a modular way to be easily extendable with additional tasks and datasets.

show abstract

Towards Knowledge Graphs Validation Through Weighted Knowledge Sources

Cited by 8 publications

References 24 publications

Extending Safety Control Structures: A Knowledge Graph for STAMP

Extending Safety Control Structures: A Knowledge Graph for STAMP

Interactive Search on the Web: The Story So Far

DBkWik++- Multi Source Matching of Knowledge Graphs

Contact Info

Product

Resources

About