Ontology Learning Algorithm Research Articles

EXPLORING BIM AND NLP APPLICATIONS: A SCIENTOMETRIC APPROACH

In AECO (Architecture, Engineering, Construction and Owner-operated) industry information are mainly defined and exchanged in natural language through textual files and documents. On the contrary, a Building Information Modeling (BIM) approach requires machine processable data and information. Natural Language Processing (NLP) allows to process textual information into structured format. About BIM in AECO industry, and NLP in different sectors, several literature reviews have been conducted. However, none of them highlighted the possible connections between the two topics. This study provides a scientometric analysis aiming to investigate possible combined applications of BIM and NLP. A quantitative literature review approach is employed, using data visualization and science mapping applied on bibliometric meta-data. The performed analysis uncovered possible directions for further research on NLP and BIM combined applications in AECO sector. Most active authors, key research patterns, and institutional affiliations are identified. The main applications areas of a combined NLP and BIM approach in AECO are: Information Retrieval and Information Enrichment of BIM models, Automatic Compliance Checking, and Safety and Risk Management. The keywords pattern analysis highlighted the main tools which allows to link Semantic BIM and NLP methods and technologies, i.e. Ontology and Machine Learning algorithms. The scientometric analysis also reveals a gap related to the Preliminary design and Requirement definition phases, highlighting a possible research area not covered by the Academia as of now.

ProGOMap: Automatic Generation of Mappings From Property Graphs to Ontologies

Property Graph databases (PGs) are emerging as efficient graph stores with flexible schemata. This raises the need to have a unified view over heterogenous data produced from these stores. Ontology based Data Access (OBDA) has become the most dominant approach to integrate heterogeneous data sources by providing a unified conceptual view (ontology) over them. The corner stone of any OBDA system is to define mappings between the data source and the target (domain) ontology. However, manual mapping generation is time consuming and requires great efforts. This paper proposes ProGOMap ( Pro perty G raph to O ntology M apper) system that automatically generates mappings from property graphs to a domain ontology. ProGOMap starts by generating a putative ontology with direct axioms from PG. A novel ontology learning algorithm is proposed to enrich the putative ontology with subclass axioms inferred from PG. The putative ontology is then aligned to an existing domain ontology using string similarity metrics. Another algorithm is proposed to align object properties between the two ontologies considering different modelling criteria. Finally, mappings are generated from alignment results. Experiments were done on eight data sets with different scenarios to evaluate the effectiveness of the generated mappings. The experimental results achieved mapping accuracy up to 97% and 81% when addressing PG-to-ontology terminological and structural heterogeneities, respectively. Ontology learning by inferring subclass axioms from a property graph helps to address the heterogeneity between the PG and ontology models.

SVM-Based Multi-Dividing Ontology Learning Algorithm and Similarity Measuring on Topological Indices

Ontology is one of the oldest terminologies in physics and is used to describe the origin and most essential attributes of all things in the world. With the development of contemporary science, ontology was given a specific definition and then introduced into the computer science as a conceptual model to describe the relationship between objects. In the past decade, the algorithms and applications in the ontology-related field have attracted the attention of many scholars. Most of the computational formulas in ontology algorithms are out of heuristic design ideas. For example, researchers use the ontology's own structural characteristics to design a calculation formula for a specific ontology from four different perspectives: name, instance, structure and attribute. In this paper, we first focus on how to apply these valuable heuristic elements to ontology learning and prediction. We combine these four heuristic elements with deep learning network and back propagation methods to obtain new ontology algorithm for prediction applications. Second, a support vector machines based multi-dividing ontology learning algorithm is proposed. Finally, we pay attention to the similarity of topological indices in chemical graph theory, and apply SVM-based multi-dividing ontology learning algorithms to give some calculation results of similarity between topological indices.

Graph Learning-Based Ontology Sparse Vector Computing

The ontology sparse vector learning algorithm is essentially a dimensionality reduction trick, i.e., the key components in the p-dimensional vector are taken out, and the remaining components are set to zero, so as to obtain the key information in a certain ontology application background. In the early stage of ontology data processing, the goal of the algorithm is to find the location of key components through the learning of some ontology sample points, if the relevant concepts and structure information of each ontology vertex with p-dimensional vectors are expressed. The ontology sparse vector itself contains a certain structure, such as the symmetry between components and the binding relationship between certain components, and the algorithm can also be used to dig out the correlation and decisive components between the components. In this paper, the graph structure is used to express these components and their interrelationships, and the optimal solution is obtained by using spectral graph theory and graph optimization techniques. The essence of the proposed ontology learning algorithm is to find the decisive vertices in the graph Gβ. Finally, two experiments show that the given ontology learning algorithm is effective in similarity calculation and ontology mapping in some specific engineering fields.

Approximation analysis of ontology learning algorithm in linear combination setting

In the past ten years, researchers have always attached great importance to the application of ontology to its relevant specific fields. At the same time, applying learning algorithms to many ontology algorithms is also a hot topic. For example, ontology learning technology and knowledge are used in the field of semantic retrieval and machine translation. The field of discovery and information systems can also be integrated with ontology learning techniques. Among several ontology learning tricks, multi-dividing ontology learning is the most popular one which proved to be in high efficiency for the similarity calculation of tree structure ontology. In this work, we study the multi-dividing ontology learning algorithm from the mathematical point of view, and an approximation conclusion is presented under the linear representation assumption. The theoretical result obtained here has constructive meaning for the similarity calculation and concrete engineering applications of tree-shaped ontologies. Finally, linear combination multi-dividing ontology learning is applied to university ontologies and mathematical ontologies, and the experimental results imply that the higher efficiency of the proposed approach in actual applications.

Mapping ontology vertices to a line using hypergraph framework

As a conceptual semantic tool, ontology is widely used in many disciplines such as genetics, nutrition, and social sciences. The key issues for ontology applications are similarity calculations and ontology alignment. In recent years, various machine learning methods and computational models have been widely used in ontology optimization and computation. The core idea is to map the entire ontology graph into one-dimensional data, such as on a real axis or on a natural number set. Through the analysis of the previous multi-dividing ontology algorithm, the technique of achieving dimensionality reduction comes from the pairwise comparison of the ontology sample vertices. The weakness of such tricks is that only two ontology vertices can be extracted for comparison at a time, which causes the number of vertex pairs to be compared in the optimization model to become very large as the totally ontology sample size increases. This paper proposes a new class of ontology learning strategies, which aims to arrange the ontology concepts into one-dimensional data according to the sequence of natural numbers. The ontology optimization model does not compare two ontology vertices, but compares a set of ontology vertices and calculates the weight of each vertex by means of random walk calculating. Each set of compared ontology vertices constitutes a hyperedge, and thus the ontology sample sets and the computational framework are represented by hypergraph and its associated bipartite graph. The algorithm proposed in this paper has potential guiding significance and theoretical value for engineering applications. In addition, two examples are presented to illustrate that our hypergraph based ontology learning algorithm is effective for a specific application background.

Theoretical Perspective of Multi-Dividing Ontology Learning Trick in Two-Sample Setting

The multi-dividing ontology learning framework has been proven to have a higher efficiency for tree-structured ontology learning, and in this work, we consider a special setting of this learning framework in which ontology sample set for each rate is divided into two groups. This setting can be regarded as the classic two-sample learning problem associated with multi-dividing ontology framework. In this work, we mainly focus on the theoretical analysis of multi-dividing two-sample ontology learning algorithm, whose ontology objective function is proposed, and the generalization bounds in this setting is obtained in terms of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$U$ </tex-math></inline-formula> -statistics technique. The theoretical result given is of potential guiding significance in the field of ontology engineering applications.

Knowledge Repository of Ontology Learning Tools from Text

Ontologies are one of the fundamental elements of the Semantic Web, and they have gained a lot of popularity and recognition because they are viewed as the answer to the need for interoperable semantics in modern information systems. The intermingling of techniques in areas such as natural language processing, information retrieval, machine learning, data mining, and knowledge representation provide a lot of possibilities for development of ontology learning approaches. A rise in focus on the ability to cope with the scale of Web data required for ontology learning forces the potential growth of cross-language research, emphasizing the automatic or semi-automatic generation of the tools dedicated to text mining and information extraction. This paper presents the integration of ontology learning tools from text in the knowledge repository to incorporate the applied techniques and outputs of an ontology learning algorithm into the one complex multifunctional solution. The proposed knowledge repository covers various applicability of existing techniques of learning ontologies from text, and offers competency question-based reasoning mechanism for individuals to specify their profiles of ontology learning tools. The validation stage is also provided in the form of applied reasoning.

Ontology learning algorithm using weak functions

AbstractOntology is widely used in information retrieval, image processing and other various disciplines. This article discusses how to use machine learning approach to solve the most essential similarity calculation problem in multi-dividing ontology setting. The ontology function is regarded as a combination of several weak ontology functions, and the optimal ontology function is obtained by an iterative algorithm. In addition, the performance of the algorithm is analyzed from a theoretical point of view by statistical methods, and several results are obtained.

Fundamental ideas and mathematical basis of ontology learning algorithm

As a data utility and aided tool, ontology has been widely used in many areas of the computer. Owing to its great efficiency, ontologies have also been introduced into various engineering disciplines. In this paper, we present the fundamental ideas of how to deal with similarity measuring problem i n ontology learning algorithms. The mathematical basis of ontology learning algorithms is also introduced from a statistical learning theory point of view. Finally, we present two ontology learning algorithms in multi-dividing setting and ontology sparse vector learning setting, respectively.

Partial multi-dividing ontology learning algorithm

As an effective data representation, storage, management, calculation and model for analysis, ontology has attracted more and more attention by researchers and it has been applied to various engineering disciplines. In the background of big data, the ontology is expected to increase the amount of data information and the structure of its corresponding ontology graph has become more important due to its complexity. It demands that the ontology algorithm must be more efficient than before. In a specific engineering application, the ontology algorithm is required to find in a quick way the semantic matching set of the concept and rank it back to the user according to their similarities. Therefore, to use learning tricks to get better ontology algorithms is an open problem nowadays.The aim of the present paper is to present a partial multi–dividing ontology algorithm with the aim of obtaining an efficient approach to optimize the partial multi–dividing ontology learning model. For doing it we state several theoretical results from a statistical learning theory perspective. Moreover, we present five experiments in different engineering fields to show the precision of our partial multi-dividing algorithm from angles of ontology, similarity measuring and ontology mapping building point of view.

CrumbTrail: An efficient methodology to reduce multiple inheritance in knowledge graphs

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.

Ontology learning algorithm for similarity measuring and ontology mapping using linear programming

Ontology learning algorithm for similarity measuring and ontology mapping using linear programming

Learning domain taxonomies: the TaxoLine approach

PurposeThe aim of this paper is to present an online framework for building a domain taxonomy, called TaxoLine, from Web documents automatically.Design/methodology/approachTaxoLine proposes an innovative methodology that combines frequency and conditional mutual information to improve the quality of the domain taxonomy. The system also includes a set of mechanisms that improve the execution time needed to build the ontology.FindingsThe performance of the TaxoLine framework was applied to nine different financial corpora. The generated taxonomies are evaluated against a gold-standard ontology and are compared to state-of-the-art ontology learning methods.Originality/valueThe experimental results show that TaxoLine produces high precision and recall for both concept and relation extraction than well-known ontology learning algorithms. Furthermore, it also shows promising results in terms of execution time needed to build the domain taxonomy.

Distance learning techniques for ontology similarity measuring and ontology mapping

Recent years, a large amount of ontology learning algorithms have been applied in different disciplines and engineering. The ontology model is presented as a graph and the key of ontology algorithms is similarity measuring between concepts. In the learning frameworks, the information of each ontology vertex is expressed as a vector, thus the similarity measuring can be determined via the distance of the corresponding vector. In this paper, we study how to get an optimal distance function in the ontology setting. The tricks we presented are divided into two parts: first, the ontology distance learning technology in the setting that the ontology data have no labels; then, the distance learning approaches in the setting that the given ontology data are carrying real numbers as their labels. The result data of the four simulation experiments reveal that our new ontology trick has high efficiency and accuracy in ontology similarity measure and ontology mapping in special engineering applications.

An Improved Ontology Learning Algorithm from Relational Schema

An Improved Ontology Learning Algorithm from Relational Schema

Ontology algorithm using singular value decomposition and applied in multidisciplinary

As a popular data management and computation tool, ontology is widely used in material science, biological genetics, chemistry, biology and pharmaceuticals. It can be regarded as a dictionary or a database, and the key of various ontology applications is similarity measuring between concepts in ontology. In this paper, we propose a new ontology learning algorithm for ontology similarity measuring and ontology mapping by means of singular value decomposition method and deterministic sampling iteration. Then, the new ontology learning is applied in plant science, gene biology, bionics and physics ontologies. The data results show the high efficiency of our singular value decomposition based ontology learning algorithm for ontology similarity measuring and ontology mapping.

Ontology computation for graph spaces focus on partial vertex pairs

The essence of all kinds of ontology applications is similarity measuring. In recent years, a variety of learning approaches are introduced to ontology similarity computation and ontology mapping. The purpose of these ontology learning technologies is to get an ontology score function which maps each vertex to a real number, and then the similarity between ontology vertices are judged according to the difference of their scores. However, such learning data should containing all pairs of sample vertices. In this paper, we raise a new ontology learning algorithm in which its training sample set only contains important edges (vertex pair) of which the similarities are to be determined by us here. Our method is based on the Kronecker kernel technologies and the solution is attributed to solving the linear system. Two simulation experiments reveal that our new ontology learning model has higher precision ratio on plant ontology and humanoid robotics ontology for similarity measuring and ontology mapping applications.

Distance computation of ontology vector for ontology similarity measuring and ontology mapping

In recent years, various kinds of learning techniques are applied in ontology similarity measuring and ontology mapping algorithms. The essence of these learning tricks is attributed to obtaining obtain a score function which is employed for calculating the similarity between vertices. Since each vertex’s related information is denoted as a p dimensional vector, the similarity between ontology vertices is equivalent to determine the distance between their correspond vectors in the high dimensional space. In this paper, we raise a new ontology learning algorithm for ontology similarity measuring and ontology mapping by means of distance computation for ontology vectors. The optimal ontology distance function is learned in terms of regularization and first-order approaches. Then, two experiments using two different kinds of ontology convex function are presented. The result data show the effectiveness of our new ontology learning algorithm in special engineering applications.

Ranking based ontology learning algorithm for similarity measuring and ontology mapping using representation theory

Ontology, as a semantic analysis and computation framework, has been widely used in various ways. Recently, learning algorithms have been employed for ontology similarity measuring and ontology mapping which aims to get a score ontology function and thus map each vertex on ontology graph to a real number. In this paper, ranking learning approach is employed in ontology function learning. The framework is designed based on reproducing kernel Hilbert space technology and representation theory trick. Finally, four experiments are manifested for the application of ontology algorithms in different fields. The effectiveness is proved by the comparison between data results.