Data linking over RDF knowledge graphs: A survey

Assi, Ali; Mcheick, Hamid; Dhifli, Wajdi

doi:10.1002/cpe.5746

Cited by 9 publications

(6 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RDF stores have become increasingly popular as a means to make knowledge available on the web (Assi et al, 2020). We propose an automatic metric for assessing the entity-based semantic adequacy of RDF verbalisers and show that it is effective in highlighting semantic inadequacy even for state-ofthe-art models with high BLEU scores.…”

Section: Discussionmentioning

confidence: 99%

Entity-Based Semantic Adequacy for Data-to-Text Generation

Faille¹,

Gatt²,

Gardent³

2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

While powerful pre-trained language models have improved the fluency of text generation models, it remains difficult to ensure that the generated texts are semantically faithful to the input. In this paper, we introduce a novel automatic evaluation metric, Entity-Based Semantic Adequacy, which can be used to assess to what extent generation models that verbalise RDF (Resource Description Framework) graphs produce text that contains mentions of the entities occurring in the RDF input. This is important as RDF subject and object entities make up 2/3 of the input. We use our metric to compare 25 models from the WebNLG Shared Tasks and we examine correlation with results from human evaluations of semantic adequacy. We show that while our metric correlates with human evaluation scores, this correlation varies with the specifics of the human evaluation setup. This suggests that in order to measure the entity-based adequacy of generated texts, an automatic metric such as the one proposed here might be more reliable, as less subjective and more focused on correct verbalisation of the input, than human evaluation measures.

show abstract

Section: Discussionmentioning

confidence: 99%

Entity-Based Semantic Adequacy for Data-to-Text Generation

Faille¹,

Gatt²,

Gardent³

2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

show abstract

“…In each iteration, we categorized the tokens into different themes based on their authors' descriptions to refine our classification. Some tokens were found in multiple clusters in subsequent iterations -as in the case where Assi et al [26] mentioned that "the incorrectness simply refers to the data typographical errors"-which can affect the value of a predicate as well as on the predicate itself. As a result of the first iteration, we were unable to classify some heterogeneities, which prompted us to establish a fifth primary level called "Problem at graph level".…”

Section: An Iterative Methodologymentioning

confidence: 99%

“…* Data quality dimension: for the problems of transgression of good practice, heterogeneity of value type or non-updated dataset. • Assi et al [26] address the issue of IM. They introduce the scalability problem when it comes to IM on large datasets.…”

Section: Review Of Articles Addressing Different Heterogeneity Issuesmentioning

confidence: 99%

“…Through these five articles, we were able to identify 69 descriptions of heterogeneity (See Table 2). 13 [26] In order to better refer to them, we established a summary fact-sheet for each type of heterogeneity encountered, identified by a token. The tokens have been colored according to the authors who report them, as shown in Figure 4 presenting one of these summary fact-sheet.…”

Section: Review Of Articles Addressing Different Heterogeneity Issuesmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Linking Problem Types for Linking Semantic Data

Conde Salazar,

Jonquet,

Symeonidou

2023

Knowledge Graphs: Semantics, Machine Learning, and Languages

View full text Add to dashboard Cite

As the number of RDF datasets published on the semantic web continues to grow, it becomes increasingly important to efficiently link similar entities between these datasets. However, the performance of existing data linking tools, often developed for general purposes, seems to have reached a plateau, suggesting the need for more modular and efficient solutions. In this paper, we propose –and formalize in OWL– a classification of the different Linking Problem Types (LPTs) to help the linked data community identify upstream the problems and develop more efficient solutions. Our classification is based on the description of heterogeneity reported in the literature –especially five articles– and identifies five main types of linking problems: predicate value problems, predicate problems, class problems, subgraph problems, and graph problems. By classifying LPTs, we provide a framework for understanding and addressing the challenges associated with semantic data linking. It can be used to develop new solutions based on existing modularized tools addressing specific LPTs, thus improving the overall efficiency of data linking.

show abstract

“…Tasks such as data cleaning, resolving inconsistencies, and standardizing formats can be undertaken during this stage. Semantic technologies like RDF (Resource Description Framework) (Assi, Mcheick, and Dhifli 2020) and OWL (Web Ontology Language) (Chen, Jia, and Xiang 2020) may also help in facilitating this process as they structure the data into a format that is machine-readable.…”

Section: E-liability Knowledge Graph Data Acquisition and Processingmentioning

confidence: 99%

AI-Driven E-liability Knowledge Graphs: A Comprehensive Framework for Supply Chain Carbon Accounting and Emissions Liability Management

Oladeji,

Mousavi,

Roston

2024

AAAI-SS

View full text Add to dashboard Cite

While carbon accounting plays a fundamental role in our fight against climate change, it is not without its challenges. We begin the paper with a critique of the conventional carbon accounting practices, after which we proceed to introduce the E-liability carbon accounting methodology and Emissions Liability Management (ELM) originally proposed by Kaplan and Ramanna, highlighting their strengths. Recognizing the immense value of this novel approach for real-world carbon accounting improvement, we introduce a novel data-driven integrative framework that leverages AI and computation, the E-Liability Knowledge Graph framework, to achieve real-world implementation of the E-liability carbon accounting methodology. In addition to providing a path-to-implementation, our proposed framework brings clarity to the complex environmental interactions within supply chains, thus enabling better informed and more responsible decision-making. We analyze the implementation aspects of this framework and conclude with a discourse on the role of this AI-aided knowledge graph in ensuring the transparency and decarbonization of global supply chains.

show abstract

Data linking over RDF knowledge graphs: A survey

Cited by 9 publications

References 105 publications

Entity-Based Semantic Adequacy for Data-to-Text Generation

Entity-Based Semantic Adequacy for Data-to-Text Generation

Classification of Linking Problem Types for Linking Semantic Data

AI-Driven E-liability Knowledge Graphs: A Comprehensive Framework for Supply Chain Carbon Accounting and Emissions Liability Management

Contact Info

Product

Resources

About