While there has been a trend in the last decades for publishing large-scale and highly-interconnected Knowledge Graphs (KGs), their users often get overwhelmed by the task of understanding their content as a result of their size and complexity. Data profiling approaches have been proposed to summarize large KGs into concise and meaningful representations, so that they can be better explored, processed, and managed. Profiles based on schema patterns represent each triple in a KG with its schema-level counterpart, thus covering the entire KG with profiles of considerable size. In this paper, we provide empirical evidence that profiles based on schema patterns, if explored with suitable mechanisms, can be useful to help users understand the content of big and complex KGs. ABSTAT provides concise pattern-based profiles and comes with faceted interfaces for profile exploration. Using this tool we present a user study based on query completion tasks. We demonstrate that users who look at ABSTAT profiles formulate their queries better and faster than users browsing the ontology of the KGs. The latter is a pretty strong baseline considering that many KGs do not even come with a specific ontology to be explored by the users. To the best of our knowledge, this is the first attempt to investigate the impact of profiling techniques on tasks related to knowledge graph understanding with a user study.

Integrating deep learning techniques, particularly language models (LMs), with knowledge representation techniques like ontologies has raised widespread attention, urging the need of a platform that supports both paradigms. Although packages such as OWL API and Jena offer robust support for basic ontology processing features, they lack the capability to transform various types of information within ontologies into formats suitable for downstream deep learning-based applications. Moreover, widely-used ontology APIs are primarily Java-based while deep learning frameworks like PyTorch and Tensorflow are mainly for Python programming. To address the needs, we present DeepOnto, a Python package designed for ontology engineering with deep learning. The package encompasses a core ontology processing module founded on the widely-recognised and reliable OWL API, encapsulating its fundamental features in a more “Pythonic” manner and extending its capabilities to incorporate other essential components including reasoning, verbalisation, normalisation, taxonomy, projection, and more. Building on this module, DeepOnto offers a suite of tools, resources, and algorithms that support various ontology engineering tasks, such as ontology alignment and completion, by harnessing deep learning methods, primarily pre-trained LMs. In this paper, we also demonstrate the practical utility of DeepOnto through two use-cases: the Digital Health Coaching in Samsung Research UK and the Bio-ML track of the Ontology Alignment Evaluation Initiative (OAEI).

Neuro-Symbolic Artificial Intelligence (AI) focuses on integrating symbolic and sub-symbolic systems to enhance the performance and explainability of predictive models. Symbolic and sub-symbolic approaches differ fundamentally in how they represent data and make use of data features to reach conclusions. Neuro-symbolic systems have recently received significant attention in the scientific community. However, despite efforts in neural-symbolic integration, symbolic processing can still be better exploited, mainly when these hybrid approaches are defined on top of knowledge graphs. This work is built on the statement that knowledge graphs can naturally represent the convergence between data and their contextual meaning (i.e., knowledge). We propose a hybrid system that resorts to symbolic reasoning, expressed as a deductive database, to augment the contextual meaning of entities in a knowledge graph, thus, improving the performance of link prediction implemented using knowledge graph embedding (KGE) models. An entity context is defined as the ego network of the entity in a knowledge graph. Given a link prediction task, the proposed approach deduces new RDF triples in the ego networks of the entities corresponding to the heads and tails of the prediction task on the knowledge graph (KG). Since knowledge graphs may be incomplete and sparse, the facts deduced by the symbolic system not only reduce sparsity but also make explicit meaningful relations among the entities that compose an entity ego network. As a proof of concept, our approach is applied over a KG for lung cancer to predict treatment effectiveness. The empirical results put the deduction power of deductive databases into perspective. They indicate that making explicit deduced relationships in the ego networks empowers all the studied KGE models to generate more accurate links.

Artificial intelligence systems are not simply built on a single dataset or trained model. Instead, they are made by complex data science workflows involving multiple datasets, models, preparation scripts, and algorithms. Given this complexity, in order to understand these AI systems, we need to provide explanations of their functioning at higher levels of abstraction. To tackle this problem, we focus on the extraction and representation of data journeys from these workflows. A data journey is a multi-layered semantic representation of data processing activity linked to data science code and assets. We propose an ontology to capture the essential elements of a data journey and an approach to extract such data journeys. Using a corpus of Python notebooks from Kaggle, we show that we are able to capture high-level semantic data flow that is more compact than using the code structure itself. Furthermore, we show that introducing an intermediate knowledge graph representation outperforms models that rely only on the code itself. Finally, we report on a user survey to reflect on the challenges and opportunities presented by computational data journeys for explainable AI.

Wikidata is a collaborative multi-purpose Knowledge Graph (KG) with the unique feature of adding provenance data to the statements of items as a reference. More than 73% of Wikidata statements have provenance metadata; however, few studies exist on the referencing quality in this KG, focusing only on the relevancy and trustworthiness of external sources. While there are existing frameworks to assess the quality of Linked Data, and in some aspects their metrics investigate provenance, there are none focused on reference quality. We define a comprehensive referencing quality assessment framework based on Linked Data quality dimensions, such as completeness and understandability. We implement the objective metrics of the assessment framework as the Referencing Quality Scoring System – RQSS. The system provides quantified scores by which the referencing quality can be analyzed and compared. RQSS scripts can also be reused to monitor the referencing quality regularly. Due to the scale of Wikidata, we have used well-defined subsets to evaluate the quality of references in Wikidata using RQSS. We evaluate RQSS over three topical subsets: Gene Wiki, Music, and Ships, corresponding to three Wikidata WikiProjects, along with four random subsets of various sizes. The evaluation shows that RQSS is practical and provides valuable information, which can be used by Wikidata contributors and project holders to identify the quality gaps. Based on RQSS, the average referencing quality in Wikidata subsets is 0.58 out of 1. Random subsets (representative of Wikidata) have higher overall scores than topical subsets by 0.05, with Gene Wiki having the highest scores amongst topical subsets. Regarding referencing quality dimensions, all subsets have high scores in accuracy, availability, security, and understandability, but have weaker scores in completeness, verifiability, objectivity, and versatility. Although RQSS is developed based on the Wikidata RDF model, its referencing quality assessment framework can be applied to KGs in general.

Robust estimation of concept similarity is crucial for applications of AI in the commercial, biomedical, and publishing domains, among others. While the related task of word similarity has been extensively studied, resulting in a wide range of methods, estimating concept similarity between nodes in Wikidata has not been considered so far. In light of the adoption of Wikidata for increasingly complex tasks that rely on similarity, and its unique size, breadth, and crowdsourcing nature, we propose that conceptual similarity should be revisited for the case of Wikidata. In this paper, we study a wide range of representative similarity methods for Wikidata, organized into three categories, and leverage background information for knowledge injection via retrofitting. We measure the impact of retrofitting with different weighted subsets from Wikidata and ProBase. Experiments on three benchmarks show that the best performance is achieved by pairing language models with rich information, whereas the impact of injecting knowledge is most positive on methods that originally do not consider comprehensive information. The performance of retrofitting is conditioned on the selection of high-quality similarity knowledge. A key limitation of this study, similar to prior work lies in the limited size and scope of the similarity benchmarks. While Wikidata provides an unprecedented possibility for a representative evaluation of concept similarity, effectively doing so remains a key challenge.

This work describes the application of semantic web standards to data quality governance of data production pipelines in the architectural, engineering, and construction (AEC) domain for Ordnance Survey Ireland (OSi). It illustrates a new approach to data quality governance based on establishing a unified knowledge graph for data quality measurements across a complex, heterogeneous, quality-centric data production pipeline. It provides the first comprehensive formal mappings between semantic models of data quality dimensions defined by the four International Organization for Standardization (ISO) and World Wide Web Consortium (W3C) data quality standards applied by different tools and stakeholders. It provides an approach to uplift rule-based data quality reports into quality metrics suitable for aggregation and end-to-end analysis. Current industrial practice tends towards stove-piped, vendor-specific and domain-dependent tools to process data quality observations however there is a lack of open techniques and methodologies for combining quality measurements derived from different data quality standards to provide end-to-end data quality reporting, root cause analysis or visualisation. This work demonstrated that it is effective to use a knowledge graph and semantic web standards to unify distributed data quality monitoring in an organisation and present the results in an end-to-end data dashboard in a data quality standards-agnostic fashion for the Ordnance Survey Ireland data publishing pipeline.

Industrial standards provide guidelines for data modeling to ensure interoperability between stakeholders of an industry branch (e.g., robotics). Most frequently, such guidelines are provided in an unstructured format (e.g., pdf documents) which hampers the automated validations of information objects (e.g., data models) that rely on such standards in terms of their compliance with the modeling constraints prescribed by the guidelines. This raises the risk of costly interoperability errors induced by the incorrect use of the standards. There is, therefore, an increased interest in automatic semantic validation of information objects based on industrial standards. In this paper we focus on an approach to semantic validation by formally representing the modeling constraints from unstructured documents as explicit, machine-actionable rules (to be then used for semantic validation) and (semi-)automatically extracting such rules from pdf documents. While our approach aims to be generically applicable, we exemplify an adaptation of the approach in the concrete context of the OPC UA industrial standard, given its large-scale adoption among important industrial stakeholders and the OPC UA internal efforts towards semantic validation. We conclude that (i) it is feasible to represent modeling constraints from the standard specifications as rules, which can be organized in a taxonomy and represented using Semantic Web technologies such as OWL and SPARQL; (ii) we could automatically identify modeling constraints in the specification documents by inspecting the tables ( P = 87 %) and text of these documents (F1 up to 94%); (iii) the translation of the modeling constraints into formal rules could be fully automated when constraints were extracted from tables and required a Human-in-the-loop approach for constraints extracted from text.

Occupant feedback enables building managers to improve occupants’ health, comfort, and satisfaction. However, acquiring continuous occupant feedback and integrating this feedback with other building information is challenging. This paper presents a scalable method to acquire continuous occupant feedback and directly integrate this with other building information. Semantic web technologies were applied to solve data interoperability issues. The Occupant Feedback Ontology was developed to describe feedback semantically. Next to this, a smartwatch app – Mintal – was developed to acquire continuous feedback on indoor environmental quality. The app gathers location, medical information, and answers on short micro surveys. Mintal applied the Occupant Feedback Ontology to directly integrate the feedback with linked building data. A case study was performed to evaluate this method. A semantic digital twin was created by integrating linked building data, sensor data, and occupant feedback. Results from SPARQL queries gave more insight into an occupant’s perceived comfort levels in the Open Flat. The case study shows how integrating feedback with building information allows for more occupant-centric decision support tools. The approach presented in this paper can be used in a wide range of use cases, both within and without the architecture, building, and construction domain.

Thesauri are popular, as they represent a manageable compromise – they are well-understood by domain experts, yet formal enough to boost use cases like semantic search. Still, as the thesauri size and complexity grow in a domain, proper tracking of the concept references to their definitions in normative documents, interlinking concepts defined in different documents, and keeping all the concepts semantically consistent and ready for subsequent conceptual modeling, is difficult and requires adequate tool support. We present TermIt, a web-based thesauri manager aimed at supporting the creation of thesauri based on decrees, directives, standards, and other normative documents. In addition to common editing capabilities, TermIt offers term extraction from documents, including a web document annotation browser plug-in, tracking term definitions in documents, term quality and ontological correctness checking, community discussions over term meanings, and seamless interlinking of concepts across different thesauri. We also show that TermIt features better fit the E-government scenarios in the Czech Republic than other tools. Additionally, we present the feasibility of TermIt for these scenarios by preliminary user experience evaluation.