Search

Real-world semantic or knowledge-based systems can become large and complex, e.g., in the biomedical domain. Tool support for the localization and repair of faults within knowledge bases of such systems can therefore be essential for their practical success. Correspondingly, a number of knowledge base debugging approaches, in particular for ontology-based systems, were proposed in recent years. Query-based debugging is a comparably recent interactive approach that localizes the true cause of an observed problem by asking knowledge engineers a series of questions. Concrete implementations of this approach exist, such as the OntoDebug plug-in for the ontology editor Protégé. To validate that a newly proposed method is favorable over an existing one, researchers often rely on simulation-based comparisons. Such an evaluation approach however has certain limitations and often cannot fully inform us about a method's true usefulness. We therefore conducted a range of user studies to assess the practical value of query-based ontology debugging. One main insight from the studies is that the considered interactive approach is indeed more efficient than an alternative algorithmic debugging based on test cases. We also observed that users frequently made errors in the process, which highlights the importance of a careful design of the queries that users need to answer. [ABSTRACT FROM AUTHOR]

Abstract Object recognition is a cornerstone task in autonomous and/or assistance systems like robots, autonomous vehicles, or those assisting to visually impaired, aiming to achieve a certain level of understanding of their surroundings. Probabilistic models, such as Conditional Random Fields (CRFs), have been successfully applied to this end given their ability to exploit contextual and situation information, e.g. a bowl is typically found in a cabinet and not in a night-stand. In this work we propose to evolve CRFs into Ontology-based Conditional Random Fields (ob CRFs), which define a multi-level structure where each level assigns a category with different granularity to the same set of objects. For example, a level could assign to an object the category appliance or furniture , while the next one could categorize it into the tv , microwave , cabinet , or table types. In this way, general categorizations can guide the classification into more specialized ones (and vice versa), improving recognition success, and mitigating the CRFs limitations when modeling a high number of object categories (shared, in general, by Machine Learning techniques). To set the categories in each level we propose to mimic the hierarchical structure of ontologies, where categories are naturally codified following a subsumption ordering. This leads us to the second advantage of ob CRFs : the multi-labeling of objects provides a richer understanding of the scene, which can be leveraged for accomplishing high-level tasks (e.g. object search or scheduling). Our approach has been tested with scenes from two state-of-the-art datasets: Robot@Home and Cornell-RGBD , outperforming the results provided by standard CRFs. Highlights • A novel model for object recognition called Ontology-based CRF is proposed. • It uses a multiple-level structure mimicking the subsumption ordering of Ontologies. • Each level jointly categorizes the same set of objects with different granularity. • Granularity ranges from specialized types (oven, fridge) to general ones (appliance). • The proposal has been assessed with the Robot@Home and Cornell-RGBD datasets. [ABSTRACT FROM AUTHOR]

Abstract Background: The process of adding new knowledge in the form of rules to already running Clinical Decision Support Systems (CDSSs) in hospitals is extremely costly and time consuming. There are two principal limitations: (1) the lack of a broad consensus regarding a uniform representation of clinical rules; and (2) the integration of new rule-based knowledge into hospital information systems. Objective: To provide a guideline with which to support knowledge acquisition for rule-based CDSSs and to facilitate the integration of that knowledge into hospital datasets using standard clinical terminologies and ontologies as reference elements. Materials and Methods: We have designed a straightforward 4-step methodology with which to incorporate the external knowledge sources and data integration required to run CDSSs in hospitals. This lightweight methodology is based on a reference ontology that integrates standard clinical terminologies and its objective is to effectively acquire procedural knowledge in the form of rules. Results: We have applied the methodology in the context of antimicrobial stewardship at a hospital. Recommendations from the European Committee on Antimicrobial Susceptibility Testing (EUCAST) were added to WASPSS, a CDSS running at the hospital. The reference ontology combines a subset of ATC terminologies for antibiotics and those of NCBI for microorganisms, including 584 and 1714 concepts, respectively. A total of 94 new rules were added to the CDSS so as to represent EUCAST knowledge. We also evaluated different implementations in order to study their scalability, during which time we analysed Drools 7.5 as a production rule engine, HermiT as an ontology reasoner and RuQAR as an integration tool. Our experiments show that the combination of a production rule engine and an ontology reasoner in runtime is more efficient than using a single rule engine with a knowledge base derived from the reference ontology (1.9 times faster than the next approach when executing 1000 expert rules on an ontology of 1000 concepts). Discussion: The methodology proposed helped to implement the knowledge acquisition process of EUCAST rules in a running CDSS. This methodology is applicable to other clinical domains when knowledge can be modelled with rules. Since it is a lightweight methodology, different implementation strategies are possible. The use of clinical standards also facilitates the future interoperation between CDSSs, particularly when using SNOMED as a reference ontology and employing future rule-sharing standards. [ABSTRACT FROM AUTHOR]

Abstract The objective of drug repositioning is to apply existing drugs to different diseases or medical conditions than the original target, and thus alleviate to a certain extent the time and cost expended in drug development. Our system RESKO, RE positioning drugs using S ide Effects and K nowledge from O ntologies, identifies drugs with similar side-effects which are potential candidates for use elsewhere, the supposition is that similar side-effects may be caused by drugs targeting similar proteins and pathways. RESKO, integrates drug chemical data, protein interaction and ontological knowledge. The novel aspects of our system include a high level of biological knowledge through the use of pathway and biological ontology integration. This provides a explanation facility lacking in most of the existing methods and improves the repositioning process. We evaluate the shared side effects from the eight conventional Alzheimer drugs, from which sixty-seven candidate drugs based on a side-effect commonality were identified. The top 25 drugs on the list were further investigated in depth for their suitability to be repositioned, the literature revealed that many of the candidate drugs appear to have been trialed for Alzheimer’s disease. Thus verifying the accuracy of our system, we also compare our technique with several competing systems found in the literature. [ABSTRACT FROM AUTHOR]

Abstract Data veracity is one of the main issues regarding Web data. Truth Discovery models can be used to assess it by estimating value confidence and source trustworthiness through analysis of claims on the same real-world entities provided by different sources. Many studies have been conducted in this domain. True values selected by most models have the highest confidence estimation. This naive strategy cannot be applied to identify true values when there is a partial order among values that is considered to enhance the final performance. Indeed, in this case, the resulting estimations monotonically increase with respect to the partial order of values. The highest confidence is always assigned to the most general value that is implicitly supported by all the others. Thus, using the highest confidence as criterion to select the true values is not appropriate because it will always return the most general values. To address this problem, we propose a post-processing procedure that, leveraging the partial order among values and their monotonic confidence estimations, is able to identify the expected true value. Experimental results on synthetic datasets show the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

In this paper we present CrumbTrail , an algorithm to clean large and dense knowledge graphs. CrumbTrail removes cycles, out-of-domain nodes and non-essential nodes, i.e., those that can be safely removed without breaking the knowledge graph’s connectivity. It achieves this through a bottom-up topological pruning on the basis of a set of input concepts that, for instance, a user can select in order to identify a domain of interest. Our technique can be applied to both noisy hypernymy graphs – typically generated by ontology learning algorithms as intermediate representations – as well as crowdsourced resources like Wikipedia, in order to obtain clean, domain-focused concept hierarchies. CrumbTrail overcomes the time and space complexity limitations of current state-of-art algorithms. In addition, we show in a variety of experiments that it also outperforms them in tasks such as pruning automatically acquired taxonomy graphs, and domain adaptation of the Wikipedia category graph. [ABSTRACT FROM AUTHOR]

Zero-Shot Classification (ZSC) has received much attention recently in computer vision research. Traditional classifiers are unable to handle ZSC because test data labels are significantly different from training data labels. Attribute-based methods have long dominated ZSC. However, classical attribute-based methods fail to distinguish between discriminative attributes and non-discriminative attributes and do not distinguish the different contributions each attribute makes to classification. We propose CORL (Combining Ontology and Reinforcement Learning) for ZSC. CORL first obtains hierarchical classification rules from attribute annotations of object classes based on ontology. These rules contain only discriminative attributes. Reinforcement learning is used to adaptively determine the discriminative degrees of the rules. The most discriminative rules are then selected for ZSC. Experiments on three benchmark datasets showed that CORL achieved higher accuracies than baseline classifiers. This suggests that CORL effectively discovers the most discriminative rules for ZSC. [ABSTRACT FROM AUTHOR]

In this paper, an ontology-supported case-based reasoning approach for computer-aided tolerance specification is proposed. This approach firstly considers the past tolerance specification problems and their schemes as previous cases and the new tolerance specification problems as target cases and uses an ontology to represent previous and target cases. Then certain ontology-based similarity measure is used to assess the similarity between the toleranced features of target and previous cases, the similarity between the part features of target and previous cases, and the similarity between the topological relations of target and previous cases. Based on these similarities, an ontology-based similarity measure for computing the similarity between target and previous cases is designed, and an algorithm for establishing such similarity measure with high accuracy and retrieving similar previous cases for a target case with this similarity measure is presented. This algorithm shows how to linearly combine the similarity of toleranced features, the similarity of part features, and the similarity of topological relations to assess the similarity between target and previous cases to implement retrieval of previous cases under the prerequisite of ensuring the highest accuracy of the similarity measure. The paper also reports a prototype implementation of the proposed approach, provides an example to illustrate how the approach works, and evaluates the approach via theoretical and experimental comparisons. [ABSTRACT FROM AUTHOR]

The classification of domain entities into top-level ontology concepts remains an activity performed manually by an ontology engineer. Although some works focus on automating this task by applying machine-learning approaches using textual sentences as input, they require the existence of the domain entities in external knowledge resources, such as pre-trained embedding models. In this context, this work proposes an approach that combines the term representing the domain entity and its informal definition into a single text sentence without requiring external knowledge resources. Thus, we use this sentence as the input of a deep neural network that contains a language model as a layer. Also, we present a methodology used to extract two novel datasets from the OntoWordNet ontology based on Dolce-Lite and Dolce-Lite-Plus top-level ontologies. Our experiments show that by using the transformer-based language models, we achieve promising results in classifying domain entities into 82 top-level ontology concepts, with 94% regarding micro F1-score. [ABSTRACT FROM AUTHOR]

Humans are able to estimate the depth of objects in their environment even using only one eye through the use of what are known as monocular cues. In this paper, we aim to integrate human knowledge and human-like reasoning used for monocular depth estimation within deep neural networks. The idea is to support the network in order to help it learn in an explicit and fast way the essential cues for the target task. For this purpose, we investigate the possibility of directly integrating geometric, semantic, and contextual information into the monocular depth estimation process. We propose exploiting an ontology model in a deep learning context to represent the urban environment as a structured set of concepts linked with semantic relationships. Monocular cues information are extracted through reasoning performed on the proposed ontology and are fed together with the RGB image in a multistream way into the deep neural network for depth estimation. Our approach is validated and evaluated on widespread benchmark datasets: KITTI, CityScapes, and AppolloScape. The obtained results show that the proposed method improves upon the state-of-the-art monocular depth estimation deep models and shows promising results regarding cross-evaluation, mainly for unseen driving scenarios. [ABSTRACT FROM AUTHOR]

In this paper, we present a forgetting-based approach to handling inconsistency in DL-Lite. Our proposed approach cannot only characterize distance-based reasoning, which is proven to rationally draw meaningful conclusions even from inconsistent DL-Lite knowledge bases but also recovery the consistency of DL-Lite knowledge bases. We first present vectors forgetting for DL-Lite by extending predicates forgetting in DL-Lite and show the predicates to be forgotten which are obtained by computing minimal hitting sets. Moreover, we develop algorithms to compute those predicates by employing Reiter’s HS-tree method and then analyze the computational complexity of those proposed algorithms. Finally, we implement our proposed algorithms and evaluate them on both consistent and inconsistent ontologies. Besides, we discuss some applications of vectors forgetting in privacy protection. [ABSTRACT FROM AUTHOR]

Recommendation systems or recommender systems (RSs) are very popular in entertainment websites. With the combination of neural networks and collaborative filtering, Neural Collaborative Filtering (NCF) recommendation methods have shown their outperformance in making item suggestions. However, the lack of semantic relationships between objects makes the NCF unable to capture the complex user–item interactions. Moreover, traditional NCF is unable to capture the dynamic user preference over time. To address these issues, in this paper, we propose novel semantic-enhanced NCF models which are applied to movie rating prediction and movie recommendation. Therefore, MovieLens and IMDB datasets are taken into account as case studies. The proposed models are the integration of ontology-like modeling and deep learning for recommendation tasks into two parts:(1) building the semantic knowledge base for movies and (2) building the user behavior analytic model that has semantic knowledge inference on the knowledge base combined with the sequential preference learned from user sessions, input into the NCF module for making predictions or recommendations. Several experiments have been conducted to show their better recommendation performance than the traditional NCF model. [Display omitted] • Building the semantic knowledge base for enhancing deep learning models. • Building the user behavior analytic model with the semantic knowledge base. • Experiments show the proposed models are significantly better than the original NCF. [ABSTRACT FROM AUTHOR]

Ontologies are commonly used as a strategy for knowledge representation. However, they are still presenting limitations to model domains that require broad forms of temporal reasoning. This study is part of the Onto-mQoL project and was motivated by the real need to extend static ontologies with diverse time concepts, relations and properties, which go beyond the commonly used Allen's Interval Algebra. Therefore, we use the n-ary relations as the basis for temporal structures, which minimally modify the original ontology, and extend these structures with a generic set of time concepts (moments and intervals), time concept properties (precise and uncertain), time relations (interval–interval, interval–moment, and moment–moment), and time relation properties (qualitative and quantitative). We divided the scientific contribution of this study into three parts. Firstly, we present the ontological temporal model (classes and properties) and how it is integrated into static ontologies. Secondly, we discuss the creation of axioms that give the semantics for precise temporal elements. Finally, as our main contribution, these ideas are extended with axioms for uncertain time. All these elements follow the Ontology Web Language (OWL) standards, so this proposal is still compatible with the main ontology editors and reasoners currently available. A case example demonstrates the use of this approach in the nutrition assessment domain. • Semantics definition of precise and uncertain time notions and relations. • Support for representations of different levels of uncertainty between events. • Compatibility with the current Semantic Web standards. • Knowledge engineering method to include time notion in static ontologies. [ABSTRACT FROM AUTHOR]

When ontologies reach a certain size and complexity, faults such as inconsistencies, unsatisfiable classes or wrong entailments are hardly avoidable. Locating the incorrect axioms that cause these faults is a hard and time-consuming task. Addressing this issue, several techniques for a semi-automatic fault localization in ontologies have been proposed and extensively studied. One class of these approaches involve a human expert who provides answers to system-generated queries about the intended (correct) ontology in order to reduce the possible fault locations. To suggest as informative questions as possible, existing methods draw on various algorithmic optimizations as well as heuristics. However, these computations are often based on certain assumptions about the interacting expert. In this work, we demonstrate that these assumptions might not always be adequate and discuss consequences of their violations. In particular, we characterize a range of expert types with different query answering behavior and show that existing approaches are far from achieving optimal efficiency for all of them. In addition, we find that the cost metric adopted by state-of-the-art techniques might not always be realistic and that a change of metric has a decisive impact on the best choice of query answering strategy. As a remedy, we suggest a new – and simpler – type of expert question that leads to a stable fault localization performance for all analyzed expert types and effort metrics, and has numerous further advantages over existing techniques. Moreover, we present an algorithm which computes and optimizes this new query type in worst-case polynomial time and which is fully compatible with existing concepts (e.g., query selection heuristics) and infrastructure (e.g., debugging user interfaces) in the field. Comprehensive experiments on faulty real-world ontologies attest that the new querying method is substantially and statistically significantly superior to existing techniques both in terms of the number of necessary expert interactions and in terms of the query computation time. We find that relying on the new querying method can save an interacting expert more than 80% of their work, and can reduce the expert's waiting time for the next query by more than three orders of magnitude. Beside these findings, we demonstrate that the efficiency of existing query-based tools can be significantly boosted by suggesting an appropriate query answering strategy to an expert; we also make recommendations in this regard. Further, we suggest optimal configurations of a debugger for situations where the new type of query is used. Remarkably, the proposed approach is not only applicable to ontologies, but to any monotonic knowledge representation language, and can even be adopted to solve general model-based diagnosis problems expressible using Reiter's theory. [ABSTRACT FROM AUTHOR]

The rapid proliferation of text data has lead to an increase in the use of Information Extraction (IE) techniques to automatically extract key information in a fast and effective manner. Relation Extraction (RE), a sub-task of IE focuses on extracting semantic relations from free natural language text and is crucial for further applications including Question Answering, Information Retrieval, Knowledge Base construction, Text Summarization, etc. Literature shows that supervised learning approaches were widely used in RE. However, the performance of supervised methodologies depend on the availability of domain-specific annotated datasets which is not viable for many of the domains including legal, financial, insurance etc. In recent times, Open Information Extraction (OIE) techniques address this issue, by facilitating domain-independent extraction of relations from large text corpora with no demand for domain-specific tagged data and predefined relation classes. Even though OIE systems are fast and simple to implement, they are less effective in handling complex sentences, and often produce redundant extractions. This paper proposes an efficient RE system to extract domain-specific relations from natural language text, consisting of Knowledge-based and Semi-supervised learning systems, integrated with domain ontology. We evaluated the performance of proposed work on 'judicial domain" as a use case and found that it overcomes the flaws and limitations of existing RE approaches, by achieving better results in terms of precision and recall. On further analysis, we found that the proposed system outperforms existing cutting-edge OIE systems on varying sentence length and complexity. • Automatic extraction of semantic relations from large volume of natural language text belonging to closed domain, particularly judicial domain. • Combination of knowledge based and semi-supervised learning systems to extract domain-specific relations from complex text that lacks domain-specific labelled data. • Solution to various challenges in handling complex sentences in passive voice and containing conjunctive forms. • Evaluation of state-of-the-art open information extraction approaches on judicial text with varying complexity and length. • First attempt to provide a solution for extracting domain-specific relations from judicial text. [ABSTRACT FROM AUTHOR]

E-learning and online education have made great strides in the recent past. It has moved from a knowledge transfer model to a highly intellect, swift and interactive proposition capable of advanced decision-making abilities. Two challenges have been observed during the exploration of recent developments in e-learning. Firstly, to incorporate e-learning systems effectively in the evolving semantic web environment and secondly, to realize adaptive personalization according to the learner's changing behavior. An ontology-driven system has proposed to implement the Felder-Silverman learning style model in addition to the learning contents, to validate its integration with the semantic web environment. Software agents are employed to monitor the learner's actual learning style and modify them accordingly. The learner's learning style and their modifications are made within the proposed e-learning system. Cloud storage is used as the primary back-end in order to maintain the ontology, databases and other required server resources. To verify the system, comparisons are made between the information presented and adaptive learning styles of the learner along with actions of agents according to learners' behavior. Finally, various conclusions are drawn by exploring the learner's behavior in an adaptive environment for the proposed e-learning system. [ABSTRACT FROM AUTHOR]

Linked Data has become a vast repository with billions of triples available in thousands of datasets. One of the challenges in integrating, querying and reusing the Linked Data is obtaining the ontology to which the datasets conform. Although many ontologies are built manually, many RDF (Resource Description Framework) datasets are still published without any prescribed schema. In this study, we propose a parallel ontology mining approach. Ontology axioms are obtained through statistical measures by running SPARQL queries. To improve efficiency, large Linked Data is divided into blocks based on the connectivity of property graphs. Mining process is then executed on parallel computing units. The division method conforms that mining results from the parallel computing units are complete and correct. Evaluations are performed on two kinds of DBpedia datasets, namely, Mapping-based Dataset with ontology and Raw Infobox Dataset without ontology and the results show the effectivity and efficiency of our approach. [ABSTRACT FROM AUTHOR]

Because of its wide potential applications, remote sensing (RS) image semantic segmentation has attracted increasing research interest in recent years. Until now, deep semantic segmentation network (DSSN) has achieved a certain degree of success on semantic segmentation of RS imagery and can obviously outperform the traditional methods based on hand-crafted features. As a classic data-driven technique, DSSN can be trained by an end-to-end mechanism and is competent for employing low-level and mid-level cues (i.e., the discriminative image structure) to understand RS images. However, its interpretability and reliability are poor due to the nature weakness of the data-driven deep learning methods. By contrast, human beings have an excellent inference capacity and can reliably interpret RS imagery with the basic RS domain knowledge. Ontological reasoning is an ideal way to imitate and employ the domain knowledge of human beings. However, it is still rarely explored and adopted in the RS domain. As a solution of the aforementioned critical limitation of DSSN, this study proposes a collaboratively boosting framework (CBF) to combine the data-driven deep learning module and knowledge-guided ontology reasoning module in an iterative manner. The deep learning module adopts the DSSN architecture and takes the integration of the original image and inferred channels as the input of the DSSN. In addition, the ontology reasoning module is composed of intra- and extra-taxonomy reasoning. More specifically, the intra-taxonomy reasoning directly corrects misclassifications of the deep learning module based on the domain knowledge, which is the key to improve the classification performance. The extra-taxonomy reasoning aims to generate the inferred channels beyond the current taxonomy to improve the discriminative performance of DSSN in the original RS image space. On the one hand, benefiting from the referred channels from the ontology reasoning module, the deep learning module using the integration of the original image and referred channels can achieve better classification performance than only using the original image. On the other hand, better classification results from the deep learning module further improve the performance of the ontology reasoning module. As a whole, the deep learning and ontology reasoning modules are mutually boosted in the iterations. Extensive experiments on two publicly open RS datasets such as UCM and ISPRS Potsdam show that our proposed CBF can outperform the competitive baselines with a large margin. [ABSTRACT FROM AUTHOR]

The Semantic Web uses ontological descriptions, in particularly Web Ontology Language OWL, as a universal medium to formally describe and exchange knowledge of various domains. Currently, many OWL ontologies for different domains come into being successively. Therefore, how to store OWL ontologies becomes one of ordinary needs of the Semantic Web. Based on the efficient storage mechanism of object-oriented databases, they may be used to store OWL ontologies for realizing the management of large amounts of knowledge in the Semantic Web. To this end, the main objective of this paper is to investigate how to store OWL ontologies in object-oriented databases, and we propose a formal approach and develop a prototype tool for storing OWL ontologies in object-oriented databases. Firstly , after giving a complete formal definition of OWL ontologies, we propose an overall architecture of storing OWL ontologies in object-oriented databases. Based on the architecture, we further give storage rules and explain how to store OWL ontologies in object-oriented databases with a running example in detail. The correctness and quality of the storage approach are proved and analyzed. Finally , we implement a prototype tool which can store OWL ontologies in a widely used open source object database db4o. Also, a query interface is developed in the prototype tool for querying the stored OWL ontologies. The storage and query examples are provided to show that the approach is feasible and the tool is efficient. [ABSTRACT FROM AUTHOR]

Within the last years, probabilistic causality has become a very active research topic in artificial intelligence and statistics communities. Due to its high impact in various applications involving reasoning tasks, machine learning researchers have proposed a number of techniques to learn Causal Bayesian Networks. Within the existing works in this direction, few studies have explicitly considered the role that decisional guidance might play to alternate between observational and experimental data processing. In this paper, we go further by introducing a serendipitous strategy to elucidate semantic background knowledge provided by the domain ontology to learn the causal structure of Bayesian Networks. We also complement our contribution with an enrichment process by which it will be possible to reuse these causal discoveries, support the evolving character of the semantic background and make an ontology evolution. Finally, the proposed method will be validated through simulations and real data analysis. [ABSTRACT FROM AUTHOR]

With the profusion of RDF resources and Linked Data, ontology alignment has gained significance in providing highly comprehensive knowledge embedded in disparate sources. Ontology alignment, however, in Linking Open Data (LOD) has traditionally focused more on the instance-level rather than the schema-level. Linked Data supports schema-level alignment, provided that instance-level alignment is already established. Linked Data is a hotbed for instance-based schema alignment, which is considered a better solution for aligning classes with ambiguous or obscure names. This study proposes an instance-based schema alignment algorithm, IUT, which builds a unified taxonomy to discover subsumption and equivalence relations between two classes. A scaling algorithm is also developed that reduces pair-wise similarity computations during the taxonomy construction. The IUT is tested with DBpedia and YAGO2, and compared with two state-of-the-art schema alignment algorithms in light of four alignment tasks with different combinations of the two data sets. The experiment results show that the IUT outperforms the two algorithms in efficiency and effectiveness, and demonstrate the IUT can provide an instance-based schema alignment solution with scalability and high performance, for ontologies containing a large number of instances in LOD. [ABSTRACT FROM AUTHOR]

An intelligent tutoring system plays vital role in education and its importance is constantly increasing, meanwhile the key challenge in the teaching learning process is assessing students’ learning efficiently. In this paper, a hybrid assessment based-on ACT-R cognitive learning theory, combining ontology knowledge map with skills is proposed. In order to assess how well students master knowledge structure, an ontology knowledge map is constructed to describe declarative knowledge; and in order to assess how well students master knowledge skills, a problem solving process is constructed to describe procedural knowledge based on ACT-R. Finally, a student’s mastery of knowledge is assessed through both the knowledge map and skills in the problem solving process, as well as auxiliary indicators like time usage, prior knowledge level, self-assessment, etc. This method is implemented in a geometric intelligent assessment system and is evaluated in a junior high school. Experiments show that the assessment results are consistent with students’ actual learning levels. The hybrid cognitive assessment method can not only obtain the score of students’ mastery of knowledge points and the structure through knowledge map, but also assess the learning skills in problem solving process through exercises quantitatively. [ABSTRACT FROM AUTHOR]

With the development of the Semantic Web (SW), the creation of ontologies to formally conceptualize our understanding of various domains has widely increased in number. However, the conceptual and terminological differences (a.k.a semantic heterogeneity problem ) between ontologies form a major limiting factor towards their use/reuse and full adoption in practical settings. A key solution to addressing this problem can be through identifying semantic correspondences between the entities (including concepts, relations, and instances) of heterogeneous ontologies, and consequently achieving interoperability between them. This process is also known as ontology alignment . The output of this process can be further exploited to merge ontologies into a single coherent ontology. Indeed, this is widely regarded as a crucial, yet difficult task, specifically when dealing with heavyweight ontologies that consist of hundreds of thousands of concepts. To address this issue, various ontology merging approaches have been proposed. These approaches can be classified into three categories: single-strategy-based approaches, multiple-strategy-based approaches, and approaches based on exploiting external semantic resources. In this paper, we first discuss the strengths and limitations of each of these approaches, and then present our framework for addressing the semantic heterogeneity problem through merging domain-specific ontologies based on multiple external semantic resources. The novelty of the proposed approach is mainly based on employing knowledge represented by multiple external resources (knowledge bases in our work) to make aggregated decisions on the semantic correspondences between the entities of heterogeneous ontologies. Other important issues that we attempt to tackle in the proposed framework are: (i) Identifying and handling inconsistency of semantic relations between the ontology concepts and, (ii) Handling the issue of missing background knowledge (such as concepts and instances) in the exploited knowledge bases by utilizing an integrated statistical and semantic technique. Additionally, the proposed solution soundly enriches the knowledge bases with missing background knowledge, and thus enables the reuse of the newly obtained knowledge in future ontology merging tasks. To validate our proposal, we tested the framework using the OAEI 2009 benchmark and compared the produced results with state-of-the-art syntactic and semantic based systems. In addition, we utilized the proposed techniques to merge three heavyweight ontologies from the environmental domain. [ABSTRACT FROM AUTHOR]

An ontology represents a consensus on the representation of the concepts and axioms of a given domain. This consensus is often reached through an iterative process, each iteration consisting in modifying the current version of the consensus. Furthermore, frequent and continuous changes are also occurring when the represented domain evolves or when new requirements have to be considered. Consequently, ontologies have to be adaptable to handle evolution, revision and refinement. However, this process is highly challenging as it is often difficult to understand all affected ontology parts when changes are performed. Thus, inconsistencies can occur in the ontology as the changes can introduce contradictory axioms. To address this issue, this paper presents a formal approach for evolving ontologies using Typed Graph Grammars. This method relies on the algebraic approach Simple PushOut (SPO) of graph transformations. It formalizes the ontology changes and proposes an a priori approach of inconsistencies resolution. The modified ontology does not need an explicit checking as an incorrect ontology version cannot actually be generated. To validate our proposal, an implementation is presented using the Attributed Graph Grammar (AGG) toolbox. [ABSTRACT FROM AUTHOR]

As the core building blocks of the Semantic Web, ontologies provide shared vocabularies and conceptual knowledge for specific application fields. At the same time, ontologies can restrict their individuals and relationships through their semantic schema. However, logical conflicts of an ontology are often inevitably unavoidable in actual application scenarios when the ontology contains any form of disjointness or negation. Generally, logical conflicts can be divided into incoherence and inconsistency. Reasoning with incoherent ontologies may obtain many redundant relationships, and incoherence is a potential cause of inconsistency which seriously affects the correctness of semantic reasoning Therefore, handling incoherence is imperative, which mainly involves the fields of conflicts detection, ontology repair and justification computation. Various incoherent ontologies are indispensable to evaluate the proposed methods for handling incoherence. We provide a survey of relevant research works to study the proposed construction methods of incoherent ontologies. It is observed that incoherent ontologies in existing works still have the following limitations: (1) Lots of web pages used to download ontologies were temporarily constructed are now inaccessible; (2) Most of the existing incoherent ontologies were constructed in a simple way such as randomly adding disjointness axioms or merging ontologies through their alignments without considering all possible incoherence cases. To address the limitations, we propose a general framework to construct incoherent ontologies and design a hybrid algorithm to instantiate this framework. With the implemented construction methods, a comprehensive benchmark containing 116 ontologies is constructed. In our evaluations, incoherent ontologies in the benchmark are measured with 11 classic metrics. We then compare 5 representative ontology debugging systems and 3 repair methods. The evaluation results reveal that these ontologies could reflect different characteristics of each ontology system and repair method. All observations could guide researchers to select incoherent ontologies. The availability of our benchmark makes a contribution to the community of ontology debugging and repair fields. • The first work studies construction methods of incoherent ontologies. • Propose a framework of existing methods to construct incoherent ontologies. • Construct a benchmark of incoherent ontologies for ontology debugging community. • Conduct abundant experiments to compare ontology debugging systems. [ABSTRACT FROM AUTHOR]

Studying the literature, one can see a large number of systems that provide natural language interfaces to databases. Despite their importance, these interfaces address only one part of the problem: transforming natural language queries to SQL queries and perhaps executing them against the underlying database. To truly handle the problem, it should be possible to develop dynamically adaptable database interfaces that can (1) adjust their functional behavior on the fly using only domain knowledge and (2) dynamically bind themselves to arbitrary databases and interface with them with no (or very little) human intervention. In particular, the interfaces should have a fixed process (algorithms and codes) and rely only on domain knowledge for adapting their functionality to any arbitrary database. This paper addresses this problem by offering a free-form natural language interface agent that, given domain ontologies, can bind itself to a target database and provide a natural language interface to it. The agent system uses its ontologies to establish mappings on-the-fly between a specific domain ontology and the underlying database's metadata, and then to transform free-form natural language queries to formal SQL queries that can execute against the underlying database. The preliminary simulations using our proof-of-concept prototype showed that our system successfully attached itself to databases and achieved high recall and precision in transforming natural language queries to formal ones. • Natural language, ontology based interface to database. • Declarative approach that can be configured to any database using only ontologies. • Ontology based process to transform natural language queries to first-order logic. • Free-Form Querying to the underlying database. [ABSTRACT FROM AUTHOR]

Relevance relations constitute the core of information retrieval. Topical ontologies, such as collaborative webpage classification projects, can provide a basis for identifying and analyzing such relations. New meaningful relevance relations can be automatically inferred from these ontologies by composing existing ones. In this work, several relevance propagation models are analyzed in terms of complex network theory. Structural properties such as Characteristic path length, Clustering coefficient and Degree distribution are computed over the models in order to understand the nature of each underlying network. This analysis raises interesting points about the Small-world and Scale-free structure of some relevance propagation models. Moreover, other connectivity and centrality measures are computed to gain additional insight into the topology of relevance. Finally, the analysis is complemented by providing visualizations of the k-core decomposition of different relevance propagation models. To illustrate the generalizability of the proposed methodology the analysis is carried out on an ontology from a different domain. The major theoretical implication of this analysis is the derivation of new instruments to typify semantic networks derived from relevance relations. The results can be exploited in a pragmatic way, as the parameters and properties derived by this analysis can serve as prior knowledge to algorithms for the automatic or semi-automatic construction of semantic networks. • Relevance propagation models derived from a topic ontology are analyzed. • Several features that characterize complex networks are observed in relevance propagation models. • Measures of connectivity and centrality offer insights into the notion of relevance from a topological perspective. • Visualizations are provided to contrast topological patterns of relevance propagation models. [ABSTRACT FROM AUTHOR]

The field of information security suffers from the lack of labelled entities. This study proposes a zero-shot hybrid approach, combining a clustering algorithm with a method for representing category labels, to classify fine-grained entity typing based on unified cybersecurity ontology (UCO) to address this issue. However, certain category labels in UCO do not have distinct domain features, while certain abbreviations cannot be obtained directly from word embedding using Word2vec. Thus, we propose a new method, referred to as mixed entities and hierarchy of UCO (MEHC), to represent the category labels. Moreover, to further improve the performance of fine-grained entity typing we propose the triClustering algorithm to re-cluster coarse-grained classification results or determine corresponding types for new entities, based on the theorem that the sum of two sides of a triangle is greater than the third. The experimental results prove that our triClustering algorithm can effectively shorten the computation time and that the proposed hybrid method is superior to other baselines for information security applications. [ABSTRACT FROM AUTHOR]

The ontology matching is a significant task for data integration and semantic interoperability. Although a large number of effective ontology matching methods have been proposed in a fully automated way, user involvement during the matching process is needed for real-world applications. It has been recognized as an effective method for further improving the quality of matching, especially for very precise matching cases. However, involving users during complex matching process suffers from new challenges of how to reduce the burden on users and how to increase effective interaction. In this paper, we propose a novel periodic learning ontology matching model based on interactive grasshopper optimization algorithm to address the above-mentioned issues. This new model takes into account the periodic feedback from users during the optimization process, rather than every generation, and a roulette wheel method is introduced to select the most problematic candidate mappings to present to users, not all, and to reduce the burden on users. To ensure the effectiveness of the interaction, a reward and punishment mechanism is considered for candidate mappings to propagate the feedback of user, and to guide the search direction of the algorithm. The experiments, conducted on two interactive tracks from Ontology Alignment Evaluation Initiative (OAEI), show that the proposed model significantly improve the quality of matching. Compared to other state-of-the-art matching systems, our model outperforms other methods in almost all cases with given different error rate, which makes it one of the most advanced leaders. Finally, a typical case of data integration is studied to present how the proposed approach is able to help enterprises to harmonize product catalogs. [ABSTRACT FROM AUTHOR]

The calculation of minimal incoherence-preserving sub-TBox (MIPS) is an important task in incoherent ontology debugging. Existing approaches to this task are inefficient when debugging large incoherent ontology with a lot of unsatisfiable concepts. To resolve the problem, we first extract a clash module from the ontology and then identify the root unsatisfiable concepts from the clash module. Afterward, the minimal unsatisfiability-preserving sub-TBox (MUPS) of each root unsatisfiable concept can be calculated on the basis of the clash module. We have proved that the MIPS of an incoherent ontology is equal to the union of the MUPSes of the root unsatisfiable concepts. Our approach can successfully avoid calculating a considerable number of MUPSes irrelevant to the MIPS. Experiments with a variety of test ontologies show that the proposed approach of calculating MIPS is efficient and practical. [ABSTRACT FROM AUTHOR]

The ontology matching approaches identify correspondences among entities across ontologies, and the quality of ontology mappings is crucial for supporting knowledge sharing and reuse on the Semantic Web. In the annual Ontology Evaluation Alignment Initiative (OAEI) competitions, matching large and complex, real-world biomedical ontologies is one of the most challenging endeavors. As matching methods are basically heuristic, wrong mappings often exist in the generated alignments. The general framework of mapping validation collects candidate wrong mappings based on unsatisfiable concepts and adopts the removal strategy to gain the coherence of alignments w.r.t. source ontologies. Although it ensures logical coherence, such repairing does not necessarily guarantee the quality of mappings obtained, i.e., the disposed mappings can be positive and the retained ones can be wrong in terms of the domain knowledge intended in the ontologies per se. This can be demonstrated by the existence of incoherences when the UMLS Metathesaurus® has been used as the basis of reference alignments for OAEI biomedical ontology matching tasks. To address this problem, we propose a novel approach for repairing biomedical ontology mappings by probabilistic reasoning and belief revision techniques, featuring a combination of removal strategy and revision strategy. More concretely, mappings are transformed into probabilistic description logics (PDL) conditional constraints and their weights into probability intervals based on our designed rules. Then, the incoherence checking of mappings is reduced to solving a linear program with the constraints under the PDL semantics. For identified incoherent mappings, instead of simply discarding, we revise them by relaxing their probability intervals until the probabilistic coherence is reached. The evaluation on repairing OAEI biomedical alignments shows that our approach can be effective in retaining correct mappings and removing wrong ones. Moreover, we show that repair systems following the general framework of mapping validation have improved their performance when equipped with our revision module at the repair stage. Furthermore, feeding structural matchers with repaired alignments as seeds shows that the mappings generated by our approach lead to the best structural matching result compared with other repair systems. Being non-aggressive, our approach is suitable for applications like ontology-supported medical information retrieval, semantic annotation and indexing of medical articles, and matchmaking and ranking objects among multiple ontologies. [ABSTRACT FROM AUTHOR]

There has contradictions in timeliness and diversity in the design schemes of complex product systems. The traditional solidified knowledge template for the knowledge reuse purpose cannot meet the rapid design needs of complex products. This paper proposes a configurable knowledge ontology model (CKOM) and a corresponding design method for rapid derivation of complex products. Based on the combination of basic knowledge elements (BKE), customized knowledge elements (CKE), and assorted knowledge elements (AKE), a knowledge structural body (KSB) is constructed by unitizing knowledge ontology into units of knowledge. And a dynamic structured knowledge template configuration method based on physical form (Pf) configuration and virtual form (Vf) association is proposed. The knowledge configuration information is transmitted and parsed in XML form, and the virtual form is established to associate and dynamically configure the corresponding physical form knowledge structure. Based on the structured knowledge model configuration template, a rapid derivative design method for electronic equipment is proposed. The rapid derivation design process is divided into three stages: requirement analysis, index demonstration, and scheme formation. By establishing seven knowledge attributes, such as global, local, scope, retrieval, the required product knowledge elements, rule knowledge elements and tools are dynamically configured to realize the dynamic processing of design parameters based on configuration knowledge elements and then form a corresponding design scheme. Finally, a rapid derivation design system is developed and applied to electronic equipment, which verifies the rationality and effectiveness of the proposed model and method. • A knowledge model of unitized ontology with configurability is proposed. • A dynamic structured knowledge template is proposed and its configuration method is provided. • The method of rapid design based on configurable product knowledge and the workflow are studied. • A prototype system of rapid design is developed and a radar technical system design is taken as an example to show the research findings. [ABSTRACT FROM AUTHOR]

Ontology alignment is a fundamental task to support information sharing and reuse in heterogeneous information systems. Optimizing the combination of matchers by evolutionary algorithms to align ontology is an effective method. However, such methods have two significant shortcomings: weights need to be set manually to combine matchers, and a reference alignment is required during the optimization process. In this paper, a meta-matching approach GSOOM for automatically configuring weights and threshold using grasshopper optimization algorithm (GOA) has been proposed. In this approach, the ontology alignment problem is modeled as optimizing individual fitness of GOA. A fitness function is proposed, which includes two goals: maximizing the number of matching and the similarity score. Since it does not require an expert to provide a reference alignment, it is more suitable for real-world scenarios. To demonstrate the advantages of the approach, we conduct exhaustive experiments tasks on several standard datasets and compare its performance to other state-of-the-art methods. The experimental results illustrate that our approach is more efficiently and is significantly superior to other metaheuristic-based methods. [ABSTRACT FROM AUTHOR]

The precise classification of community service cases is the most fundamental aspect of intelligent community service systems. However, data imbalance makes it challenging to achieve the desired level of precise classification. Existing transfer learning methods use open Internet knowledge for identifying case features and mining potential feature relations. However, community service cases have the characteristics such as short text length and non-public content, which restrict the transfer learning modes. In this paper, a cross-region transfer learning method is proposed to solve the classification problem of cases with small datasets in data imbalance situation while considering the perspective of regional cooperation. First, an ontology modeling method is applied to standardize the case features, reducing the effect of semantic ambiguity on transfer results. Secondly, to improve the effectiveness of source domain classification, this paper utilizes an extended marginal fisher analysis where the distance is measured by the inner product between data. Next, the mapping matrix from target domain to source domain is learned through domain adaptation. Finally, the method is verified based on the empirical data from Lanzhou and Beidaihe in China. Experimental results on classifiers show the proposed method helps regions to improve case classification rates significantly through knowledge complementation. The proposed approach can be followed to build case-based community service systems of reasonable accuracy and limited sample sizes. • We seek to classify community service cases with small datasets in data imbalance situation. • Existing transfer learning methods have high requirements both for the length and openness of case content. • We use a cross-regional transfer learning to learn the map from local weak classes to non-local strong classes. • Classifiers equipped with learned maps may use few samples for training. • Both the cross-region semantic ambiguity and source domain feature representation are considered for effective classification. [ABSTRACT FROM AUTHOR]