Search

Industrial analytics that includes among others equipment diagnosis and anomaly detection heavily relies on integration of heterogeneous production data. Knowledge Graphs (KGs) as the data format and ontologies as the unified data schemata are a prominent solution that offers high quality data integration and a convenient and standardised way to exchange data and to layer analytical applications over it. However, poor design of ontologies of high degree of mismatch between them and industrial data naturally lead to KGs of low quality that impede the adoption and scalability of industrial analytics. Indeed, such KGs substantially increase the training time of writing queries for users, consume high volume of storage for redundant information, and are hard to maintain and update. To address this problem we propose an ontology reshaping approach to transform ontologies into KG schemata that better reflect the underlying data and thus help to construct better KGs. In this poster we present a preliminary discussion of our on-going research, evaluate our approach with a rich set of SPARQL queries on real-world industry data at Bosch and discuss our findings.

SemTab 2021 was the third edition of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, successfully collocated with the 20th International Semantic Web Conference (ISWC) and the 16th Ontology Matching (OM) Workshop. SemTab provides a common framework to conduct a systematic evaluation of state-of-the-art systems.

In the context of Industry 4.0 [1] and Internet of Things (IoT) [2], modern manufacturing and production [3, 4] lines are equipped with software systems and sensors that constantly collect and send a high volume of data.

Modern industry witnesses a fast growth in volume and complexity of heterogeneous manufacturing (big) data thanks to the technological advances of Industry 4.0, including development in perception, communication, processing, and actuation. Data has become the new oil for industries. However, despite the effort and time invested in the data business, there still exists a big room for improvement in exploiting the value of data. In particular, data is still often scattered and stored in silos affecting its usage; a lot of data generated by sensors is not used in applications; companies possess precious data but do not have a trustworthy scheme to share its value; etc. There are certainly many ways to address these issues. In this paper we discuss the dimension of meaning in data and how we address it at Bosch in a holistic semantification fashion that bestows data with meanings which has always been important for humans to perceive, comprehend, reason, and produce. We believe the emphasis, the clarification, and the promotion of the eminent and profound roles of semantic technologies in the industry should lead to considerable opportunities for advances in technology, growth of profitability, and paradigm change in the industrial practice.

This paper describes the CitySAT system that we developed for the DBpedia Answer Type (AT) prediction task of the SMART 2021 challenge. The challenge can be interpreted as a multi-class classification task that takes natural language questions and returns pairs of the predicted answer category and types. For training, we merged the SMART 2021 DBpedia dataset with the 2020 dataset given for the previous year's AT task. In this study, three local Machine Learning (ML) models are deployed to cover the three different types of task and question (category prediction, literal type prediction and resource type prediction). The best model obtains a 98.36% accuracy for the category prediction using a Logistic Regression (LR) classifier. Similarly, another LR model results in 97.90% accuracy for the literal type prediction task. Lastly we also built a Multi-Layer Perceptron (MLP) model to deal with several ontology classes (∼760 classes for DBpedia) in the resource type prediction task. The best MLP model achieves 79.34% on the merged training dataset. The final system output obtained a 98.4% accuracy, 84.2% NDCG@5, and 85.4% NDCG@10 on the (official) test dataset.

In this work we present an exploratory study to apply OWL2Vec* to drive the clustering of ontology entities (i.e., ontology clustering). OWL2Vec* is a state-of-the-art system that creates embeddings, capturing the semantics of both entities and tokens that appear in the ontology.

We present the participation of LogMap and its variants in the OAEI 2021 campaign. The LogMap project started in January 2011 with the objective of developing a scalable and logic-based ontology matching system. This is the eleventh participation in the OAEI and the experience has so far been very positive. LogMap is one of the few systems that participates in (almost) all OAEI tracks.

We present the participation of LogMap and its variants in the OAEI 2020 campaign. The LogMap project started in January 2011 with the objective of developing a scalable and logic-based ontology matching system. This is the ninth participation in the OAEI and the experience has so far been very positive. LogMap is one of the few systems that participates in (almost) all OAEI tracks.

The Ontology Alignment Evaluation Initiative (OAEI) aims at comparing ontology matching systems on precisely defined test cases. These test cases can be based on ontologies of different levels of complexity and use different evaluation modalities (e.g., blind evaluation, open evaluation, or consensus). The OAEI 2020 campaign offered 12 tracks with 36 test cases, and was attended by 19 participants. This paper is an overall presentation of that campaign.

This paper considers an answer type and category prediction challenge for a set of natural language questions, and proposes a question answering classification system based on word and DBpedia knowledge graph embeddings. The questions are parsed for keywords, nouns and noun phrases before word and knowledge graph embeddings are applied to the parts of the question. The vectors produced are used to train multiple multi-layer perceptron models, one for each answer type in a multiclass one-vs-all classification system for both answer category prediction and answer type prediction. Different combinations of vectors and the effect of creating additional positive and negative training samples are evaluated in order to find the best classification system. The classification system that predict the answer category with highest accuracy are the classifiers trained on knowledge graph embedded noun phrases vectors from the original training data, with an accuracy of 0.793. The vector combination that produces the highest NDCG values for answer category accuracy is the word embeddings from the parsed question keyword and nouns parsed from the original training data, with NDCG@5 and NDCG@10 values of 0.471 and 0.440 respectively for the top five and ten predicted answer types.

With the fundamentals of lives dependent upon the extensive use of the internet-based searches for common life items, there is an ever-growing demand of the quick and meaningful search query systems. This has given the rise of the concept called Semantic Web. There are many challenges in developing the Semantic Web however one fundamental challenge is to design systems to enable the semantic access to the information in tabular data (e.g., Web tables). In this paper, we discuss one such system which has been developed for the automatic annotation of the tabular data using a knowledge graph. We call this system LexMa. Our system is based on lexical matching techniques. LexMa has participated in the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab 2020).

We present the participation of LogMap and its variants in the OAEI 2019 campaign. The LogMap project started in January 2011 with the objective of developing a scalable and logic-based ontology matching system. This is the ninth participation in the OAEI and the experience has so far been very positive. LogMap is one of the few systems that participates in (almost) all OAEI tracks.

The Ontology Alignment Evaluation Initiative (OAEI) aims at comparing ontology matching systems on precisely defined test cases. These test cases can be based on ontologies of different levels of complexity (from simple thesauri to expressive OWL ontologies) and use different evaluation modalities (e.g., blind evaluation, open evaluation, or consensus). The OAEI 2019 campaign offered 11 tracks with 29 test cases, and was attended by 20 participants. This paper is an overall presentation of that campaign.

Transfer learning which aims at utilizing knowledge learned from one problem (source domain) to solve another different but related problem (target domain) has attracted wide research attentions. However, the current transfer learning methods are mostly uninterpretable, especially to people without ML expertise. In this extended abstract, we brief introduce two knowledge graph (KG) based frameworks towards human understandable transfer learning explanation. The first one explains the transferability of features learned by Convolutional Neural Network (CNN) from one domain to another through pre-training and fine-tuning, while the second justifies the model of a target domain predicted by models from multiple source domains in zero-shot learning (ZSL). Both methods utilize KG and its reasoning capability to provide rich and human understandable explanations to the transfer procedure., Comment: In AAAI-19 Workshop on Network Interpretability for Deep Learning

The Pistoia Alliance Ontologies Mapping Project has applied the Ontology Matching algorithm, Paxo to the laboratory analytics domain. Nine ontologies relevant to laboratory analytics were selected. Among all possible pair combinations, thirteen of Paxo’s computed mapping sets were selected for evaluation through comparison with a silver standard alignment generated from the consensus votes of a panel of systems participating in the OAEI campaign.

Ontology-based knowledge bases (KBs) like DBpedia are very valuable resources, but their usefulness and usability are limited by various quality issues. One such issue is the use of string literals instead of semantically typed entities. In this paper we study the automated canonicalization of such literals, i.e., replacing the literal with an existing entity from the KB or with a new entity that is typed using classes from the KB. We propose a framework that combines both reasoning and machine learning in order to predict the relevant entities and types, and we evaluate this framework against state-of-the-art baselines for both semantic typing and entity matching.

We present the participation of LogMap and its variants in the OAEI 2018 campaign. The LogMap project started in January 2011 with the objective of developing a scalable and logic-based ontology matching system. This is our eight participation in the OAEI and the experience has so far been very positive. LogMap is one of the few systems that participates in (almost) all OAEI tracks.

The Human Phenotype Ontology (HP) is a reference vocabulary of human phenotypic abnormalities. HP, apart from the textual information (general definitions, descriptions, synonyms, etc.) of each ontology concept, also provides computer-readable logical definitions (axioms) of terms that will allow human phenotypic abnormalities to be related to entities from anatomy, pathology, bio- chemistry and other areas. In this paper we present a prototype to generate new axiomatic knowledge from the textual descriptions of each HP term. The proto- type (i) detects terms in the textual descriptions and not found in the given logical expressions, (ii) generates pair combinations of those terms, (iii) builds triples after detecting the most probable relation between the pair of terms using a sta- tistical model and, finally, (iv) suggests the most probable triples to the user so she can decide which ones can be added to the original axioms.

Large ontologies still pose serious challenges to state-of-the-art on-tology alignment systems. In this paper we present an approach that combines alexical index, a neural embedding model and locality modules to effectively di-vide an input ontology matching task into smaller and more tractable matchingsubtasks. We have conducted a comprehensive evaluation using the datasets ofthe Ontology Alignment Evaluation Initiative. The results are encouraging andsuggest that the proposed methods are adequate in practice and can be integratedwithin the workflow of state-of-the-art systems.

The evolution of semantic structured data, such as those behind the deep web or socialnetworks, requires mapping between sources to enable a high level integration. Sev-eral ontology matching systems have been developed to establish mappings betweenmultilingual ontologies, however, employing these systems in real world requires anassessment of the ontologies capability and performance which is conducted by theMultiFarm Track. Yet, this track still lacks of ontologies from different language fami-lies. In this paper, we contribute to the OAEI initiative with a Turkish dataset to extendthe coverage of languages for the matching systems.

On Partitioning for Ontology Alignment?Sunny Pereira1, Valerie Cross1, Ernesto Jiménez-Ruiz21Miami University, Oxford, OH 45056, United States2University of Oslo, Norway1 IntroductionOntology Alignment (OA) is the process of determining the mappings between twoontologies. A number of systems currently exists and many of them are participating inthe annual Ontology Alignment Evaluation Initiative (OAEI).3Ontology alignment for two very large ontologies becomes time consuming andmemory intensive. For example, thelargebiotrack in the OAEI campaign still posesserious challenges to participants and only 4 out of 11 systems managed to completethe largestlargebiotask. A general approach to address these challenges is to partitioneach ontology into cohesive blocks. The matching task is then divided into smaller tasksinvolving only relevant pair of blocks (i.e., partitions). Ontology partitioning brings newchallenges: how best to partition each ontology into blocks and whether the partitioningprocess on each ontology should be independent of each other. Three main strategiesexist:(i)totally independent partitioning of both ontologies using various clusteringalgorithms,(ii)independent partitioning of the better structured ontology and then useits partitioning to direct the partitioning of the other, and(iii)dependent partitioningbetween the two using a quick and efficient initial mapping of the two and then thismapping directs their partitioning.A preliminary study of these three partitioning strategies and their effects on ontol-ogy alignment is presented. The objective of this preliminary work is to determine thesuitability of these strategies to improve the performance of OA systems when dealingwith large ontologies, especially those unable to cope with the largest tasks.

An increasing number of sensors are being deployed in business-critical environments, systems, and equipment; and stream a vast amount of data. The operational efficiency and effectiveness of business processes rely on domain experts’ agility in interpreting data into actionable business information. A domain expert has extensive domain knowledge but not necessarily skills and knowledge on databases and formal query languages. Therefore, centralised approaches are often preferred. These require IT experts to translate the information needs of domain experts into extract-transform-load (ETL) processes in order to extract and integrate data and then let domain experts apply predefined analytics. Since such a workflow is too time intensive, heavy-weight and inflexible given the high volume and velocity of data, domain experts need to extract and analyse the data of interest directly. Ontologies, i.e., semantically rich conceptual domain models, present an intelligible solution by describing the domain of interest on a higher level of abstraction closer to the reality. Moreover, recent ontology-based data access (OBDA) technologies enable end users to formulate their information needs into queries using a set of terms defined in an ontology. Ontological queries could then be translated into SQL or some other database query languages, and executed over the data in its original place and format automatically. To this end, this article reports an ontology-based visual query system (VQS), namely OptiqueVQS, how it is extended for a stream-temporal query language called STARQL, a user experiment with the domain experts at Siemens AG, and STARQL’s query answering performance over a proof of concept implementation for PostgreSQL. © 2017 IOS Press. This is the authors' accepted and refereed manuscript to the article.

achichi2017aOM is co-located with the 16th International Semantic Web Conference (ISWC); International audience; Ontology matching consists of finding correspondences between semantically related entities of different ontologies. The Ontology Alignment Evaluation Initiative (OAEI) aims at comparing ontology matching systems on precisely defined test cases. These test cases can be based on ontologies of different levels of complexity (from simple thesauri to expressive OWL ontologies) and use different evaluation modalities (e.g., blind evaluation, open evaluation, or consensus). The OAEI 2017 campaign offered 9 tracks with 23 test cases, and was attended by 21 participants. This paper is an overall presentation of that campaign.

We present the participation of LogMap and its variants in the OAEI 2017 campaign. The LogMap project started in January 2011 with the objective of developing a scalable and logic-based ontology matching system. This is our seventh participation in the OAEI and the experience has so far been very positive. LogMap is one of the few systems that participates in (almost) all OAEI tracks.

Ontology-based data integration (OBDI) allows users to federate over heterogeneous data sources using a semantic rich conceptual data model. An important challenge in ODBI is the curation of mappings between the data sources and the global ontology. In the last years, we have built IncMap, a system to semi-automatically create mappings between relational data sources and a global ontology. IncMap has since been put into practice, both for academic and in industrial applications. Based on the experience of the last years, we have extended the original version of IncMap in several dimensions to enhance the mapping quality: (1) IncMap can detect and leverage semantic-rich patterns in the relational data sources such as inheritance for the mapping creation. (2) IncMap is able to leverage reasoning rules in the ontology to overcome structural differences from the relational data sources. (3) IncMap now includes a fully automatic mode that is often necessary to bootstrap mappings for a new data source. Our experimental evaluation shows that the new version of IncMap outperforms its previous version as well as other state-of-the-art systems.

A number of ontology matching techniques have been proposed that rely on full disclosure of their ontological models prior to the construction of the alignment. However, within open and opportunistic environments, such approaches may not always be pragmatic or even acceptable (due to privacy concerns). Several studies have focussed on collaborative, decentralised approaches to ontology alignment, where agents negotiate the acceptability of correspondences (i.e. mappings between corresponding entities in different ontologies) acquired from past encounters, or try to ascertain novel correspondences on the fly. However, such approaches can lead to logical flaws that may undermine their utility. In this paper, we extend a dialogical approach to correspondence negotiation, whereby agents not only exchange details of possible correspondences, but also identify potential violations to the so-called conservativity principle, where novel but undesirable entailments between named concepts in one of the input ontologies emerge. We present a formal model of the dialogue, and show how \conservativity violations can be repaired (using an existing correspondence repair system) during the dialogue through the exchange of repairs. We then illustrate how agents negotiate over possible correspondences and repairs by means of a walkthrough example.

SemTab 2020 was the second edition of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, successfully collocated with the 19th International Semantic Web Conference (ISWC) and the 15th Ontology Matching (OM) Workshop. SemTab provides a common framework to conduct a systematic evaluation of state-of-the-art systems.

In this paper we present a preliminary logic-based evaluation of the integration of post-composed phenotypic descriptions with domain ontologies. The evaluation has been performed using a description logic reasoner together with scalable techniques: ontology modularization and approximations of the logical difference between ontologies., in Adrian Paschke, Albert Burger, Andrea Splendiani, M. Scott Marshall, Paolo Romano: Proceedings of the 3rd International Workshop on Semantic Web Applications and Tools for the Life Sciences, Berlin,Germany, December 8-10, 2010

The work presented in this paper is framed within the context of the BigMed project, aproject funded by the Norwegian Research Council. One of the objectives of BigMed isto enhance the phenotype acquisition process in newborns with a monogenetic disorder,one of the four patient groups studied in the project. The use of the Human PhenotypeOntology (HPO) [1] to tag phenotypes and systems like PhenoTips have substantiallycontributed to the overall phenotype acquisition workflow. PhenoTips [2] is a systemfor the acquisition of phenotypic information in patients with a genetic disease. Phe-noTips also suggests, given a selected set of HPO terms, candidate diagnoses usingOMIM (Online Mendelian Inheritance in Man) codes, and related genes for a subse-quent genetic test. Although PhenoTips represents a fantastic effort, we believe it couldbe extended with suitable Semantic Web solutions. In this paper, we present the firststeps to adopt ontology alignment techniques to contribute to the diagnostic process.

Much information is conveyed within tables, which can be semantically annotated by humans or (semi)automatic approaches. Nevertheless, many applications cannot take full advantage of semantic annotations because of the low quality. A few methodologies exist for the quality assessment of semantic annotation of tabular data, but they do not automatically assess the quality as a multidimensional concept through different quality dimensions. The quality dimensions are implemented in STILTool 2, a web application to automate the quality assessment of the annotations. The evaluation is carried out by comparing the quality of semantic annotations with gold standards. The work presented here has been applied to at least three use cases. The results show that our approach can give us hints about the quality issues and how to address them.

This paper describes STILTool, an open-source tool for the automatic evaluation of the quality of semantic annotations computed by semantic table interpretation approaches. STILTool provides a graphical interface allowing users to analyse the correctness of the annotations of tabular data. The tool also provides a set of statistics in order to identify the most common error patterns.

Table annotation is a key task to improve querying the Web and support the Knowledge Graph population from legacy sources (tables). Last year, the SemTab challenge was introduced to unify different efforts to evaluate table annotation algorithms by providing a common interface and several general-purpose datasets as a ground truth. The SemTab dataset is useful to have a general understanding of how these algorithms work, and the organizers of the challenge included some artificial noise to the data to make the annotation trickier. However, it is hard to analyze specific aspects in an automatic way. For example, the ambiguity of names at the entity-level can largely affect the quality of the annotation. In this paper, we propose a novel dataset to complement the datasets proposed by SemTab. The dataset consists of a set of high-quality manually-curated tables with non-obviously linkable cells, i.e., where values are ambiguous names, typos, and misspelled entity names not appearing in the current version of the SemTab dataset. These challenges are particularly relevant for the ingestion of structured legacy sources into existing knowledge graphs. Evaluations run on this dataset show that ambiguity is a key problem for entity linking algorithms and encourage a promising direction for future work in the field.