Automatic Ontology Construction Research Articles

Hierarchical clustering algorithm to generate ontology network

Ontologies have played a crucial role in addressing challenges related to knowledge modeling, artificial intelligence, clustering, and classification. Within the realm of web services, ontologies primarily serve to describe web service interfaces, facilitating the automation of functional processes, particularly to guide the registers in discovering services. Enriching this model with a shared ontology (knowledge base) can improve the efficiency of web services technology by guiding web services processes. This shared ontology plays the role of intermediary between queries and registries, and can be shared between different registries. However, manually constructing ontologies is a labor-intensive and expensive endeavor, necessitating domain expertise. Automatic ontology construction approaches present compelling alternatives, offering advantages in terms of both time and financial costs. In this article, we advocate for the utilization of the Hierarchical Clustering algorithm to generate an ontological network (Service Ontology (SO)) from a semantic web services corpus. Experimental validations are presented to demonstrate the effectiveness of the proposed methodology.

Enhancing relevant concepts extraction for ontology learning using domain time relevance

Concepts extraction is the backbone task for an ontology construction system. Identifying the relevant concepts is considered one of the main challenges of automatic ontology construction (called Ontology Learning (OL)). This research introduces a novel relevance metric that estimates the sustainability distribution of concepts to identify the modern and relevant concepts, called Domain Time Relevance (DTR). Also, this research proposes a Developed Concepts extraction Model based on the proposed DTR, namely DTR-DCEM. This proposed model uses the proposed Concepts extraction stopwords (CE-stopwords) list to avoid noise data. This proposed model, DTR-DCEM, aims to extract the relevant concepts from scientific publications. The experiments are conducted in two different datasets: DL2019 and ACLRelAcS. The experimental results show that the proposed model DTR-DCEM outperforms the state-of-the-art models. It got between (3.32∼51.07)% better performance than comparative models for the DL2019 dataset and between (3.29∼24.51)% better performance for the ACLRelAcS dataset. Moreover, the statistical significance of the proposed model DTR-DCEM has been proved using paired t-test.

A systematic literature review of automatic ontology construction

In recent years, ontologies have received a lot of attention as a knowledge representation technique. Constructing an ontology can be a difficult task for several reasons: it necessitates time-consuming expert work, the classification task is not as simple as it appears, and the incredible speed with which knowledge evolves in the real world forces ontology engineers to constantly update and enrich the generated ontologies with new concepts, terms, and lexicon. However, there are other ways to automate ontology construction, such as semi-automatically, where human intervention is required in one or more ontology design tasks, and fully automatically, where the entire ontology construction is delegated to a software system. In this paper, we will conduct a systematic review of literature that will focus on a comparative analysis of different techniques relating to both semi-automatic and fully automatic ontology construction using various techniques and automated algorithms applied. In these fields, the goal is to identify the domain areas, current trends, data architectures, and ongoing challenges. This paper will review academic documents published in peer-reviewed venues from 2017 to 2021, based on a four-step selection process of identification, screening, eligibility, and inclusion for the selection process. To examine these documents, a systematic review was conducted and six main research questions were answered. The results indicate that automatic ontology construction could give higher complexity, shorter time, and reduce the role of the expert knowledge to evaluate ontology than manual ontology construction. The fields that have been investigated in this survey include online retail, biomedical, public security, information security (IS), Quran, Arabic, Dubai government services, Alzheimer’s disease, agriculture, Chinese tax, job portal, sentiment, and ontology learning. Finally, we summarize the most commonly used methods in automatic ontology construction, which we believe will serve as a foundation for future multidisciplinary research.

스토리 영상 콘텐츠 분석을 위한 장면 그래프 생성 모델 기반의 자동 온톨로지 구축 프레임워크

In this paper, we propose an extended ontology automatic construction framework based on multiple deep learning models as part of an effective analysis of story video content. Semi-automatic techniques using image processing techniques have been the mainstream for the existing ontology construction methods for moving pictures, but there is a problem that human intervention is required and the accuracy is low due to the limitations of image processing techniques. To overcome this, in this paper, we propose an auto mated method based on the deep learning scene graph generation technique. In particular, in the case of video content with a story, the relationship between characters is a very important factor in understanding the scene, so deep learning-based object relationship creation model, character identification model, and important area caption generation model are applied to extract objects and recognize their relationships. And design a framework that automatically builds a domain ontology dependent on the story through procedural fusion between each model and module function. In addition, the proposed framework suggests a method for efficiently processing system requirements and system resources through meta control in the condition that requires simultaneous operation of multiple deep learning models to analyze story video content. Through this, the proposed framework effectively identifies critical region captions and object relationships in a scene in story-telling video content, and executes three types of models simultaneously. Finally, we conduct an experiment to automatically build an ontology by applying the proposed framework to specific video content, and check the effectiveness of the proposed framework.

An adaptation of Text2Onto for supporting the French language

The ontologies are progressively imposing themselves in the field of knowledge management. While the manual construction of an ontology is by far the most reliable, this task has proved to be too tedious and expensive. To assist humans in the process of building an ontology, several tools have emerged proposing the automatic or semi-automatic construction of ontologies. In this context, Text2Onto has become one of the most recognized ontology learning tools. The performance of this tool is confirmed by several research works. However, the development of this tool is based on Princeton WordNet (PWN) for English. As a result, it is limited to the processing of textual resources written in English. In this paper, we present our approach based on JWOLF, a Java API to access the free WordNet for French that we have developed to adapt this tool for the construction of ontologies from corpus in French. To evaluate the usefulness of our approach, we assessed the performance of the improved version of Text2Onto on a simplistic corpus of French language documents. The results of this experiment have shown that the improved version of Text2Onto according to our approach is effective for the construction of an ontology from textual documents in the French language.

Fuzzy Ontology-Based Querying User' Requests Under Uncertain Environment

Assistance with the use of technical devices is required as soon as the tasks to be performed become complex. This assistance is also needed as soon as the authors provide assistance to users to find solutions to incidents that occur during the application of unsuitable procedures. The goal of this work is then to provide a knowledge extraction approach that can interpret user requests into valid system requests to respond appropriately to novice user requests. This approach is based on a fuzzy semantic network for the modeling of imprecise and uncertain knowledge and the automatic construction of temporary fuzzy ontology for the identification and interpretation of user requests. The proposed approach has the advantage of being able to integrate the notion of uncertain and imprecise knowledge into the representation of system objects and procedures. The experimental results show the efficiency and the effectiveness of the approach.

Automatic ontology construction from text: a review from shallow to deep learning trend

The explosive growth of textual data on the web coupled with the increase on demand for ontologies to promote the semantic web, have made the automatic ontology construction from the text a very promising research area. Ontology learning (OL) from text is a process that aims to (semi-) automatically extract and represent the knowledge from text in machine-readable form. Ontology is considered one of the main cornerstones of representing the knowledge in a more meaningful way on the semantic web. Usage of ontologies has proven to be beneficial and efficient in different applications (e.g. information retrieval, information extraction, and question answering). Nevertheless, manually construction of ontologies is time-consuming as well extremely laborious and costly process. In recent years, many approaches and systems that try to automate the construction of ontologies have been developed. This paper reviews various approaches, systems, and challenges of automatic ontology construction from the text. In addition, it also discusses ways the ontology construction process could be enhanced in the future by presenting techniques from shallow learning to deep learning (DL).

Automatic construction of coal mine accident ontology

Automatic construction of coal mine accident ontology

Ontology Learning Procedures Based on Web Mining Techniques

Ontology establishes an approach for knowledge representation, sharing and reusing across various applications. It is also the backbone of the semantic web. Therefore, there is a requirement of rapid and effective ontology construction methodology for developing sophisticated knowledge-based and semantic web-based system. However, setting up ontology manually is a tough, time consuming, error-prone, costly, and inflexible task which requires the significant participation of a knowledge engineer or domain expert. An automatic or semi-automatic ontology construction methodology will be a better solution to this problem. Over the last decade, some attempts have been made by the researchers that provide assistance to ontology engineer to build ontologies. Still, there are several open issues in this field. The paper presents a brief overview of different tasks in relation to ontology learning method and reviews some of the ontology learning frameworks or methodologies based on web mining techniques. The comparative analysis of them in the tabular form based on the distinguishing ontology learning tasks has also been presented. Furthermore, we have discussed some of the recent problems and major drift related to the construction of ontology from semi-structured web pages.

A novel framework for biomedical entity sense induction

BackgroundRapid advancements in biomedical research have accelerated the number of relevant electronic documents published online, ranging from scholarly articles to news, blogs, and user-generated social media content. Nevertheless, the vast amount of this information is poorly organized, making it difficult to navigate. Emerging technologies such as ontologies and knowledge bases (KBs) could help organize and track the information associated with biomedical research developments. A major challenge in the automatic construction of ontologies and KBs is the identification of words with its respective sense(s) from a free-text corpus. Word-sense induction (WSI) is a task to automatically induce the different senses of a target word in the different contexts. In the last two decades, there have been several efforts on WSI. However, few methods are effective in biomedicine and life sciences. MethodsWe developed a framework for biomedical entity sense induction using a mixture of natural language processing, supervised, and unsupervised learning methods with promising results. It is composed of three main steps: (1) a polysemy detection method to determine if a biomedical entity has many possible meanings; (2) a clustering quality index-based approach to predict the number of senses for the biomedical entity; and (3) a method to induce the concept(s) (i.e., senses) of the biomedical entity in a given context. ResultsTo evaluate our framework, we used the well-known MSH WSD polysemic dataset that contains 203 annotated ambiguous biomedical entities, where each entity is linked to 2–5 concepts. Our polysemy detection method obtained an F-measure of 98%. Second, our approach for predicting the number of senses achieved an F-measure of 93%. Finally, we induced the concepts of the biomedical entities based on a clustering algorithm and then extracted the keywords of reach cluster to represent the concept. ConclusionsWe have developed a framework for biomedical entity sense induction with promising results. Our study results can benefit a number of downstream applications, for example, help to resolve concept ambiguities when building Semantic Web KBs from biomedical text.

An automatic construction of domain ontology to analyse competence prerequisites of jobs

An automatic construction of domain ontology to analyse competence prerequisites of jobs

Automatic Construction of E-Government Services Ontology from Arabic Webpages

The digital age has led to a significant increase in the amount of information, and the relationships among different types of information have become more sophisticated. In addition, growing numbers of users are benefiting from this information. The types of these users vary, necessitating techniques for analyzing customers’ experiences in order to meet their needs. Regarding e-government, the number of structured and unstructured webpages of electronic services has increased, making the repositories more complex and difficult to analyze without considering semantic knowledge. In this paper, we present an approach for the automatic extraction of the ontology-based Semantic Web (SW) constructed from Arabic webpages related to Dubai’s e-government services. The proposed methodology consists of four stages. The first stage is concerned with data extraction and validation from the www.dubai.ae portal, including official profiles for more than 500 services. We developed an Automatic Extraction Dataset System (AEDS) tool to extract the dataset that represents all government services profiles. The second stage is data processing and involved using Natural Language Processing (NLP) tasks to process the services’ profiles and extract the ontology keywords. The third stage is the mapping rules process to link the ontology components with the extracted keywords. Lastly, the ontology was constructed using the OWL format and Protégé tool standards. Afterwards, an experimental evaluation was conducted to evaluate the accuracy of the constructed ontology. The results indicate high scores in terms of Precision, with 87% on average, and Recall, with 97% on average. Finally, we present the challenges and future prospects.

An automatic construction of domain ontology to analyse competence prerequisites of jobs

In many industries, the hiring process is a critical task, where many applicants will be applied for the single position, so it is required to analyse their qualification which ought to suit the requirement. Identifying feasible candidate with the required knowledge and skills is the difficult task which is faced by the organisations. In the proposed work, this issue is rectified through domain ontology construction framework (DOCF) from the job knowledge thesis and the job requirements details, which are obtained from online. The obtained documents were clustered regarding the content and conceptual similarity-based clustering method. From those clustered documents job-know ontology will be built. So it is easy to create the information requirements about the job search phase by both candidates and the human resources (HR) of the industries. It is proved that proposed research method leads to give better result when compared with the existing research method in terms of increased accuracy rate.

Research on ontology generation and evaluation method in oil field based on the MDR

At present, domain ontology construction methods are mature, but most domain ontologies are still in manual or semi-automatic status. Based on the track research on the metadata and its registration standards, this paper proposes a method of domain ontology automatic construction based on Metadata Registration (MDR).The conceptual metamodel of MDR and the mapping rules of data describing meta model to ontology are formulated, and based on two mapping rules, this paper proposes a domain ontology based on MDR, and evaluates the domain ontology, realizes the oil field (upstream) ontology of automated construction. It is proved that the ontology method of petroleum field based on MDR is feasible and effective, and this method is also applicable to other fields.

Extracting semantic relations from the Quranic Arabic based on Arabic conjunctive patterns

There is an immense need for information systems that rely on Arabic Quranic ontologies to provide a precise and comprehensive knowledge to the world. Since semantic relations are a vital component in any ontology and many applications in Natural Language Processing strongly depend on them, this motivates the development of our approach to extract semantic relations from the Quranic Arabic Corpus, written in Arabic script, and enrich the automatic construction of Quran ontology. We focus on semantic relations resulting from proposed conjunctive patterns which include two terms with the conjunctive AND enclosed in between. The strength of each relation is measured based on the correlation coefficient. Finally, we evaluate the significance of this method by using hypotheses testing and Student t-test. The obtained results are very promising since we combine an accurate Arabic grammar with strong statistical techniques to prove the existence and measure the strength of this type of semantic relations.

Automatic Ontology Construction using Conceptualization and Semantic Roles

Ontologies are constructed to extract meaningful information from data sources. Constructing ontologies aim at capturing domain knowledge that gives a commonly agreed understanding of a domain, which may be reused, shared, among applications and groups. To ease the process of building ontologies automatically, this manuscript per the authors proposes a new approach which extracts semantic roles of nouns in the sentential structure along with usual concepts and their relationships. The extracted information about different roles, concepts and relationships among the concepts from different documents are then merged to construct an ontology for whole document. The proposed approach is implemented and the performance of the proposed technique is evaluated. Experiments show the ontology thus created captures most of the information given in the document.

Automatic Ontology Construction Using Text Corpora and Ontology Design Patterns (ODPs) in Alzheimer’s Disease

An ontology is defined as an explicit specification of a conceptualization, which is an important tool for modeling, sharing and reuse of domain knowledge. However, ontology construction by hand is a complex and a time consuming task. This research presents a fully automatic method to build bilingual domain ontology from text corpora and ontology design patterns (ODPs) in Alzheimer’s disease. This method combines two approaches: ontology learning from texts and matching with ODPs. It consists of six steps: (i) Term & relation extraction (ii) Matching with Alzheimer glossary (iii) Matching with ontology design patterns (iv) Score computation similarity term & relation with ODPs (v) Ontology building (vi) Ontology evaluation. The result of ontology composed of 381 terms and 184 relations with 200 new terms and 42 new relations were added. Fully automatic ontology construction has higher complexity, shorter time and reduces role of the expert knowledge to evaluate ontology than manual ontology construction. This proposed method is sufficiently flexible to be applied to other domains.

A Study on the Automatic Construction of Ontology

A Study on the Automatic Construction of Ontology

Automatic Construction of Domain Ontology Using Wikipedia and Enhancing it by Google Search Engine

Information and resources available on the Web are growing increasingly and web users need to have a common understanding of them. The Semantic Web whose most important role is to help machine to understand and analyze the existing data on the Web, has not been used commonly, yet. The foundation of the Semantic Web are ontologies. Ontologies play the main role in the exchange of information and development of the Lexical Web to the Semantic Web. Manual construction of ontologies is time-consuming, expensive, and dependent on the knowledge of domain engineers. Also, Ontologies that have been extracted automatically from corpus on the Web might have incomplete information. The main objective of this study is describing a method to improve and expand the information of the ontologies. Therefore, this study first discusses the automatic construction of prototype ontology in animals‟ domain from Wikipedia and then a method is presented to improve the built ontology. The proposed method of improving ontology expands ontology concepts through Bootstrapping methods using a set of concepts and relations in initial ontology and with the help of the Google search engine. A confidence measure was considered to choose the best option from the returned results by Google. Finally, the experiments showed the information that was obtained using the proposed method is twice more accurate than the information that was obtained at the stage of automatic construction of ontology from Wikipedia.

AUTOMATIC STRUCTURING OF SEMANTIC WEB SERVICES – AN APPROACH

Ontologies have become the effective modeling for various applications and significantly in the semantic web. The difficulty of extracting information from the web, which was created mainly for visualising information, has driven the birth of the semantic web, which will contain much more resources than the web and will attach machine-readable semantic information to these resources. Ontological bootstrapping on a set of predefined sources, such as web services, must address the problem of multiple, largely unrelated concepts. The web services consist of basically two components, Web Services Description Language (WSDL) descriptors and free text descriptors. The WSDL descriptor is evaluated using two methods, namely Term Frequency/Inverse Document Frequency (TF/IDF) and web context generation. The proposed bootstrapping ontological process integrates TF/IDF and web context generation and applies validation using the free text descriptor service, so that, it offers more accurate definition of ontologies. This paper uses ranking adaption model which predicts the rank for a collection of web service documents which leads to the automatic construction, enrichment and adaptation of ontologies.