Ontology Based Semantic Information Retrieval

Ontology creation poses integration and interoperability challenges. Ontology integration is a hot topic in artificial intelligence. The article considers variants for integrating ontologies in Bulgarian cultural and historical heritage, which can be used as an Intelligent Tourist Guide's knowledge base. Cataloguing standard and ontology integration mechanisms using Protégé are discussed.

Balinese people tend to have limitations in expressing their aspirations. The hereditary message that Balinese people can maintain their attitude to look good on behalf of "Bali" and other people's assessment of the "critical" thinking sometimes does not always provide an appropriate dialogue space when the Balinese express their opinions. All is kept tightly in the heart and of course requires the media to communicate as needed. The media for communication has gradually transformed from dialog to social media with appropriate technological devices. Social media is a media that carried out digitally by the public. The dominant social media device nowadays is a smartphone that makes it easy for people to reach each other even if they don't meet in the same place and time. The place and time used are all available online and through social media products like Facebook, Instagram, Twitter, Whatsapp, Line and others. Using internet data packages from each provider which has a much lower price than conventional communication media such as telephone and sms. The tagline "communication is in your hand" is already evident today. The using of social media has also entered into various generations with significant age differences. Ranging from children to old people. Social media can penetrate several communication phenomena that are blocked in the real world. One of them is the Covid19 pandemic or commonly known as the Corona Virus. The characteristic of governments around the world in responding to the emphasis on the spreading of Covid19 is to conduct physical distancing or restrictions on physical meetings between peoples. Some countries even have a lockdown. Opportunities to meet in real place are limited. One of the communication media that can be used to update the latest information is with social media. The various statuses in the form of memes, writing and audiovisual media represent the characteristics of the social media user communities. Balinese people are no exception. Government decisions addressing the Pandemic of Covid19 to peoples who underestimated the spreading of the virus at the beginning of the outbreak made various resistance reactions emerge from various social media statuses. The discourse of resistance is actually new for Balinese who tend to stay away from problems in the real world or Koh Ngomong. Since the use of massive social media, the character of Balinese people looks different in cyberplace. All become more courageous to speak up until said about the resistance by themself. Using qualitative methods and analysis based on Hegemony theory and Theory of Power and Knowledge which will lead to Theory of Practice, the writer will uncover the meaning of Balinese resistance through status writing on social media during the Pandemic Covid19. The purpose of this research is to show that there are other characters that are able to be shown by the Balinese people outside of the stigma given by most people. This character eventually becomes a real thing that the Balinese people are able to convey their thoughts flexibly while providing a meaning of resistance through status writing on social media.

Since XML becomes a crucial format for representing information, it is necessary to establish techniques for managing XML documents. A possible solution can be found in storing XML data in (object-)relational databases. For this purpose most of the existing techniques often exploit an XML schema of the stored XML data, usually expressed in DTD. But the more complex today's applications

trademark and document use rules apply. This document, developed by the Rule Interchange Format (RIF) Working Group, specifies the Basic Logic Dialect, RIF-BLD, a format that allows logic rules to be exchanged between rule systems. The RIF-BLD presentation syntax and semantics are specified both directly and as specializations of the RIF Framework for Logic Dialects, or RIF-FLD. The XML serialization syntax of RIF-BLD is specified via a mapping from the presentation syntax. A normative XML schema is also provided. Status of this Document May Be Superseded This section describes the status of this document at the time of its publication. Other documents may supersede this document. A list of current W3C publications

In general, Muslims all over the world have an innate tendency to hold fast to Islam’s teachings as narrated in the Qur’an and Hadith. The present study is an investigation on the utilization of this adherence for improving the standards of ethical behavior of Muslim IT professionals, particularly software engineers. The principal point of this paper is to develop the importance of ethics among software engineers in order to make them realize the impact of various immoral practices in their field e.g., property violations, general software upgrading, design methodology, software privacy, etc. The moral values put forward in code-of- conduct have been scrutinized from Islamic point of view by studying the same in light of verses in the Qur’an and Hadith of our beloved Prophet Muhammad (P.B.U.H.). It is high time for software engineers and developers to accept the dire need of a paradigm shift in software engineering that integrates divine revelation with reason. The paper, therefore,...

Information Retrieval (IR) is the field of computer science that deals with the storage, searching, and retrieving of the documents that satisfy the user need. Distributed Arabic Information Retrieval (DAIR) is a model enables a user to access many searchable Arabic documents reside in different locations. DAIR is more complex than the centralized Arabic IR (AIR) because it requires addressing two significant additional problems that are the resource selection and the results merging. The Arabic language is a rich in multiple meanings (senses) in a lot of words and the tasking to find the appropriate meaning is a key demand in most of the AIR applications. This paper aims to improve the efficiency of the DAIR systems through using an algorithm belong to the swarm intelligence called Artificial Bee Colony (ABC) algorithm and to improve the result quality through using the query expansion. The MABC-SDAIR algorithm is the search approach used in this work. It aims to search the most re...

This study proposed an SCA advice system. It is an ontology-based recommender that provides advice on appropriate computer curricula based on the behavior of high school students. The three computer curricula at Chiang Mai Rajabhat University include computer science (CS), information technology (IT), and web programming and security (WEB). This study aims to design the ontology framework for an SCA advice system. The system considers three core ontologies: student, computer-curriculum, and advice. After analyzing student behaviors, the behavior types of CS, IT, and WEB were determined to be SB-2, SB-1, and SB-5, respectively. All subjects in these three curricula were analyzed and grouped into seven groups. Their curricula were synthesized in terms of basic skills, basic knowledge, and characteristics. Finally, advice results can be obtained by consolidating the curriculum nature of the CS, IT, and WEB curricula.

The Quran and the Hadith are two religious texts used by Muslims as a reference to perform their daily religious obligations. Hence, developing a computational tool to better understand and link these different texts would be useful for Islamic scholars, learners, and laymen. We hypothesise that linking them using a knowledge-based approach by extending a Quran ontology to cover the Hadith is possible. However, there are several Quran ontologies and none of these were rigorously evaluated using a standard ontology evaluation method. For this reason, we start our experiment by enumerating and discussing the existing Quran ontologies. Then the best candidates of the enumerated ontologies are evaluated using a corpus-based approach to visualize the overlap between these ontologies and the Hadith. Our experiment shows that one Quran ontology could be used as a starting point for a larger scope of an Islamic ontology that covers both the Quran and Hadith.

Previous work in information retrieval have shown that using evidence, such as concepts and relations, from external knowledge sources could enhance the retrieval performance. Recently, deep neural approaches have emerged as state-of-the art models for capturing word semantics. This paper presents a new tri-partite neural document language framework that leverages explicit knowledge to jointly constrain word, concept, and document learning representations to tackle a number of issues including polysemy and granularity mismatch. We show the effectiveness of the framework in various IR tasks.

The continuous growth of information on the Internet and the availability of a large mass of electronic documents in Arabic language make Natural Language processing (NLP) tasks play an important role to enhance and facilitate the access and the exploitation of information. Among available NLP tasks, we are interested in Arabic Topic Detection. Our objective is to realize an indexing system capable of identifying the general topics discussed in Arabic unvowelized documents. The proposed topic detection system of Arabic texts is based on Mutual Information for Topic Oriented Vocabulary (TOV) and classification according to Jaccard and adapted TF-IDF indicators. The experimental results are presented in terms of precision, recall and F1 measure evaluating the influence of factors such as: vocabulary length and morphological analysis on Arabic Topic Detection.

The continuous growth of information on the Internet and the availability of a large mass of electronic documents in Arabic language make Natural Language processing (NLP) tasks play an important role to enhance and facilitate the access and the exploitation of information. Among available NLP tasks, we are interested in Arabic Topic Detection. Our objective is to realize an indexing system capable of identifying the general topics discussed in Arabic unvowelized documents. The proposed topic detection system of Arabic texts is based on Mutual Information for Topic Oriented Vocabulary (TOV) and classification according to Jaccard and adapted TF-IDF indicators. The experimental results are presented in terms of precision, recall and F1 measure evaluating the influence of factors such as: vocabulary length and morphological analysis on Arabic Topic Detection.

This study proposed an SCA advice system. It is an ontology-based recommender that provides advice on appropriate computer curricula based on the behavior of high school students. The three computer curricula at Chiang Mai Rajabhat University include computer science (CS), information technology (IT), and web programming and security (WEB). This study aims to design the ontology framework for an SCA advice system. The system considers three core ontologies: student, computer-curriculum, and advice. After analyzing student behaviors, the behavior types of CS, IT, and WEB were determined to be SB-2, SB-1, and SB-5, respectively. All subjects in these three curricula were analyzed and grouped into seven groups. Their curricula were synthesized in terms of basic skills, basic knowledge, and characteristics. Finally, advice results can be obtained by consolidating the curriculum nature of the CS, IT, and WEB curricula.

Automatic Question Answering (QA) is the process of identifying exact answer in response of question asked by the user. Several QA approaches have been proposed for many languages. One of such languages is Arabic which spoken by nearly 200 million people. Approximately 90% of Arab people are Muslims. Many Muslims need religious consultations toward specific issues. Such consultations have to be acquired from a legitimate source such as Islamic scholars. The response toward these consolations is called a Fatwa, which is considered as an Islamic point of view toward such issues. Therefore, there is a vital demand to present a QA system that has the ability to answer Muslims questions based on a collection of Fatwas. Several research efforts have been implemented to provide QA for Islamic domain. However, such efforts have used simple lists of lexicons as a source of knowledge, which leads to several limitations in terms of the correctness of the answers. This is due to the process of analyzing question would not be guided with a rich source of knowledge. Hence, this study aims to propose an ontology-based question answering approach for the domain of Islamic Fatwa. The ontology has been constructed using a collection of Fatwas, which has been collected from Ibn Uthaymeen-Prayer Fatwas. Several pre-processing tasks have been applied in order to eliminate the irrelevant data (e.g. numbers, non-Arabic letters and punctuation). Furthermore, Term Frequency-Inverse Document Frequency (TFIDF) has been used in order to provide the main concepts of the domain for ontology construction. The proposed ontology-based QA has been evaluated by comparing it with QA approach that uses simple semantic lexicon as a source of knowledge. The proposed method has outperformed the other approach by obtaining an approximately 90% of Fmeasure. This demonstrates that the use of ontology as a source of knowledge for QA would enrich the process of extracting the answers.

The social illness has become main problem in Indonesia such as drug addiction, prostitution, game addiction, and so on. Based on Indonesian government, through its anti-drug agency, the National Narcotics Board (BNN) in 2015 the number of drug users are 5 million people. Drugs have caused for as many as 15,000 deaths each year in Indonesia. Peoples did not get information about social ills such as the types of drugs that have the same characteristics. As a largest Muslim country in the world may be reduce the social ills with the Islam approach. Recently, the integration of Islamic science and technology has become popular. At times the people get obstacles to get information and advice directly from expert and scholars in Islamic science. This paper is to develop a prototype expert system by providing prevention and best treatment based on Quran and Hadith. We use some of the data for knowledge base obtained from Selat Panjang, Riau. Based on the preliminary results, it has simila...

The Holy Quran ontology models are gaining popularity among researchers due to people’s demands in understanding this divine book. Due to this, there are many studies and research have been conducted in this area to facilitate people’s understanding of the Quran. The Quran knowledge is represented conforming to an ontology within a system framework. This also includes various concepts that are interrelated with the others. From the literature, however, the existing Quranic ontology models do not cover all concepts in the Quran, which limit them to domains such as place nouns, themes, pronouns, antonyms and Islamic knowledge in the Quran. Thus, this research aims to identify relevant research works from various electronic data sources using systematic literature review (SLR) method to provide a comprehensive review of this area. This paper presents a systematic review of the literature related to the existing ontology models, where it leads to disseminating the correct knowledge of t...

Data integration in scientific experiments is important to the scientists in many research domains. This is because many experimental data involved multidiscipline areas and run in different machines or instruments which results in data stored in different ends and human intervention is required in forming a chain of data analysis. Ontology is one of the approaches that have been used in data integration in many domain areas. This paper described and reviewed ontology in data integration effort. Furthermore, the state of research for ontology-based integration of scientific experiment data also covered in this paper.

L'essor d'Internet et du Web a favorisé la mise en ligne de nombreuses informations disponibles, potentiellement utiles pour la veille technologique et scientifique d'une entreprise. Différentes techniques de recherche d'information sur le Web ont été proposées afin de construire des outils permettant d'affiner la recherche pour obtenir des résultats pertinents. Cependant, dans le contexte du Web actuel, malgré de grandes avancées dans le champ de la recherche d'information, ces outils ont montré leurs limites en termes de précision et de rappel. L'application des technologies du Web Sémantique, en particulier des ontologies, semble donc intéressante pour améliorer les performances de la tâche de veille technologique et scientifique sur le Web. Les travaux de cette thèse se sont déroulés dans le cadre d'une coopération entre le Centre Scientifique et Technique du Bâtiment (CSTB) et l'équipe ACACIA de l'INRIA Sophia Antipolis. L'objectif principal est d'exploiter les technologies du Web Sémantique pour développer un système de veille (OntoWatch), guidé par des ontologies, pour collecter, capturer, filtrer, classer et structurer le contenu du Web en provenance de plusieurs sources d'information dans un scénario d'aide à la veille technologique et scientifique. Dans une première partie, nous modélisons le processus de veille technologique et scientifique du CSTB reposant sur le modèle général de veille proposé par Lesca. Puis nous identifions les apports potentiels de l'ontologie dans les différentes étapes et nous construisons une ontologie dédiée au système de veille. Cette ontologie intègre une partie d'une ontologie existante et des vocabulaires offerts dans des thésaurus du domaine du CSTB. Ensuite, nous proposons des algorithmes utilisant une ontologie pour améliorer la recherche des documents sur le Web, puis générer automatiquement les annotations sémantiques (représentees dans le langage RDF) sur ces documents. Ces annotations alimentent dans le système les bases d'annotations, sur lesquelles repose la recherche sémantique d'informations. Enfin, nous proposons une architecture multi-agents pour l'implémentation du système OntoWatch. Nous nous focalisons en particulier sur la conception des sous-sociétés d'agents dédiées à la recherche et à l'annotation automatique des documents sur le Web.

With the increasing demand of intelligent systems capable of operating in different contexts (e.g. users on the move) the correct interpretation of the user-need by such systems has become crucial to give consistent answers to the user questions. The most effective applications addressing such task are in the fields of natural language processing and semantic expansion of terms. These techniques are aimed at estimating the goal of an input query reformulating it as an intent, commonly relying on textual resources built exploiting different semantic relations like synonymy, antonymy and many others. The aim of this paper is to generate such resources using the labels of a given taxonomy as source of information. The obtained resources are integrated into a plain classifier for reformulating a set of input queries as intents and tracking the effect of each relation, in order to quantify the impact of each semantic relation on the classification. As an extension to this, the best tradeoff between improvement and noise introduction when combining such relations is evaluated. The assessment is made generating the resources and their combinations and using them for tuning the classifier which is used to reformulate the user questions as labels. The evaluation employs a wide and varied taxonomy as a use-case, exploiting its labels as basis for the semantic expansion and producing several corpora with the purpose of enhancing the pseudo-queries estimation.

The Al-Quran is the sacred book of Muslims, and it provides God's word in the form of orders, instructions, and guidelines for people to follow to have happy lives both here and in the afterlife. Several earlier research has used ontologies to store the knowledge found in the Quran. The previous study focused on extracting the relationship between classes and instances or the "is-a relation" by classifying instances based on the referenced class. Based on the performance testing of the instances classification framework, the test results show that Support Vector Machine (SVM) with Term Frequency-Inverse Document Frequency (TF-IDF) and stemming operation had dropped the accuracy value to 65.41% when the test data size was increased to 30%. Likewise, with BPNN with TF-IDF and stemming operations. In the Indonesian Quran translation dataset with a test data size of 30%, the accuracy value drops to 57.86%. Instances classification based on the thematic topics of the Qur&#3...

Bu makalede internetteki giysi kataloglarına eri im yöntemleri üzerinde olumlu de i ikler yapmayı amaçlayan bir uygulamadan bahsedilmektedir. Hâlihazırdaki internet satı siteleri kullanıcılara giysi koleksiyonlarını sadece gezme ve metin bazlı arama imkânı vermektedirler. Bu çalı mada ise ma aza koleksiyonları üzerinde içerik bazlı bir arama sistemi geli tirilmi ve kullanıcılara aradıkları bir giysiyi bulma imkânı tanınmı tır. Deney sonuçları göz ile incelendi inde tatmin edici ba arı oranlarına ula ılmı tır. Bu çalı ma, bilinen bilgisayarla görme tekniklerini farklı bir alana uygulayarak günlük hayatta kullanılabilecek ve insanlara faydalı olabilecek bir uygulama ortaya çıkmı tır.

Knowledge management is a crucial aspect for enterprises that want to effectively cope with business innovation. However, the full control of the knowledge asset is often missing due to the lack of precise organizational models, policies, and proper technologies, especially in Virtual Enterprises (VEs), which are characterized by heterogeneous partners with different policies, skills and know-how. For such reasons, the need for technologies that enable knowledge sharing, efficient access to knowledge resources, and interoperability is felt as primary. This work proposes a semantics-based infrastructure aimed at supporting effective knowledge management for business innovation in VEs. Knowledge resources are formally represented and stored in a semantic layer, which is exploited by a set of semantic services for enabling efficient retrieval and reasoning capabilities to derive additional knowledge.

The social illness has become main problem in Indonesia such as drug addiction, prostitution, game addiction, and so on. Based on Indonesian government, through its anti-drug agency, the National Narcotics Board (BNN) in 2015 the number of drug users are 5 million people. Drugs have caused for as many as 15,000 deaths each year in Indonesia. Peoples did not get information about social ills such as the types of drugs that have the same characteristics. As a largest Muslim country in the world may be reduce the social ills with the Islam approach. Recently, the integration of Islamic science and technology has become popular. At times the people get obstacles to get information and advice directly from expert and scholars in Islamic science. This paper is to develop a prototype expert system by providing prevention and best treatment based on Quran and Hadith. We use some of the data for knowledge base obtained from Selat Panjang, Riau. Based on the preliminary results, it has simila...

Chest diseases are a subgroup of respiratory system diseases. The symptoms of these diseases are similar and this makes the diagnosis process difficult. Therefore, to ease the diagnosis process we gathered Information about fourteen diseases, which attack the chest, with their symptoms and investigations about them. In this paper, we present an Arabic ontology-based approach for chest diseases diagnosis. We focus on ontology building process. This ontology can be used to help physicians and other users, determine the chest disease that a patient is suffering from and what are the investigations that should be applied. While experts can easily gather information from this data, lay users lack the expertise needed to deal with it. Most of the efforts to solve this problem focus on the English language. So also, in this paper, we present a new approach based on natural language processing to translate Arabic language query to SPARQL query

The Question Answering (QA) system becomes essential owing to the increasing amount of web content and high demand for the right and short information. Intending to enhance QA results towards the Natural Language Processing (NLP) community, most of the Question answering system exploits machine learning algorithms to generate an appropriate answer to the user query. Even though, it lacks to predict accurately over the large-scale data by itself, needs an external force to make adjustments in the answer prediction. With the recent evolution in deep learning, the neural network architecture reflects its potential for QA. The deep learning model can determine the issues in answer prediction on their own and resolves it. The class of deep neural network such as Deep Belief Network (DBN) is widely applied in question answering especially for text processing. Moreover, most of the works on the text processing exploits the skip-gram model for representing the relevant words in the vector over a massive volume of unstructured text data. However, it results in inefficient outcomes, especially when processing the combination of frequent data and stop words. To resolve these issues, this paper introduces the Deep Neural network for Answering user queries (DNA). The proposed DNA approach performs the QA system over DBN by applying alternate skip-N gram and negative sampling. The conditional probability measurement develops an alternate skip-N gram model and alternatively applying the normal N-gram and skip-N gram model. It improves the efficiency of relevant word-pair detection without increasing the computational complexity. By only using samples, the negative sampling reduces the impact of noise on the accuracy of alternate skip-N gram model and improves the efficiency of the QA system. Finally, the DNA is evaluated using Java and compared with the existing Unified model for Document-Based Question Answering (UDBQA). The results show the efficiency of DNA, for instance, the UDBQA approach reduces the F-measure by 16.3%, compared to the DNA approach with 2000 number of queries.

Training set is the key role player that can improve the performance of any classification task. Different techniques and methods are being applied to generate training set depending on its area of application. Researchers in data science and semantic web community use different kind of training sets generated to improve the performances of classifications and information retrieval capability. Operational Training Set Generator (TSG) should always solve a minimum of two issues; (1) it must address the computational cost in producing a reasonable outcome, thereby reducing the computational cost in the whole system. The runtime of TSG is near linear as in blocking approach and (2) it must produce the qualitative training sets. We use LogTfIdf as the cosine similarity function of two given vectors to produce Bag of Words (BoW); the tokenizer is developed to specially take care of delimiters that often come across URIs and other RDF essentials. We evaluated our UTSG on nine cross-domain...

Chest diseases are a subgroup of respiratory system diseases. The symptoms of these diseases are similar and this makes the diagnosis process difficult. Therefore, to ease the diagnosis process we gathered Information about fourteen diseases, which attack the chest, with their symptoms and investigations about them. In this paper, we present an Arabic ontology-based approach for chest diseases diagnosis. We focus on ontology building process. This ontology can be used to help physicians and other users, determine the chest disease that a patient is suffering from and what are the investigations that should be applied. While experts can easily gather information from this data, lay users lack the expertise needed to deal with it. Most of the efforts to solve this problem focus on the English language. So also, in this paper, we present a new approach based on natural language processing to translate Arabic language query to SPARQL query

Development of Ontology via manual is tedious and time consuming task. Hence, the development should be either automatic of semi-automatic development. The task of semi-automatic or automatic ontology development is referring to the Ontology Learning field. Ontology Learning will learn to extract ontological elements to form an ontology. Synonym identification is one of the important activities in Ontology Learning. The process of identification can use various methods. Thus, this paper aims to experiment some important insight into synonym identification by using the seed word patterns. The experiment used two patterns which relate to the Kaabah and Al-Qiyammah. The pattern has utilized the JAPE pattern in the identification process. Result shows that the significant terms related to the both synonyms have been extracted. The pattern 1 is applicable for Hajj ontology and the pattern 2 is more general to be used for the Quranic ontology development. The extracted terms will then be ...

The social illness has become main problem in Indonesia such as drug addiction, prostitution, game addiction, and so on. Based on Indonesian government, through its anti-drug agency, the National Narcotics Board (BNN) in 2015 the number of drug users are 5 million people. Drugs have caused for as many as 15,000 deaths each year in Indonesia. Peoples did not get information about social ills such as the types of drugs that have the same characteristics. As a largest Muslim country in the world may be reduce the social ills with the Islam approach. Recently, the integration of Islamic science and technology has become popular. At times the people get obstacles to get information and advice directly from expert and scholars in Islamic science. This paper is to develop a prototype expert system by providing prevention and best treatment based on Quran and Hadith. We use some of the data for knowledge base obtained from Selat Panjang, Riau. Based on the preliminary results, it has simila...

The healthcare data can be employed to develop a health prediction system that can improve in heart disease prevention. Big data on health care, including patient records, clinical notes, diagnosis, parents and family past ailments, hospitals, and scan results can aid in the phase of disease identification and prediction. The emerging machine learning method offers an important framework for forecasting cardiac diseases. An advanced Support Vector Machine (SVM) classifier was used by the program to conduct parameter tuning to improve classification accuracy and performance. The proposed work aims to develop a real-time prediction system for health issues based on big medical data processing on the cloud. In the proposed scalable system, the medical parameters are sent to Apache Spark to extract the attributes from the data and to apply the proposed machine learning algorithm aiming to predict the healthcare risks and send them as alerts and recommendations to the users and the healt...

The continuous growth of information on the Internet and the availability of a large mass of electronic documents in Arabic language make Natural Language processing (NLP) tasks play an important role to enhance and facilitate the access and the exploitation of information. Among available NLP tasks, we are interested in Arabic Topic Detection. Our objective is to realize an indexing system capable of identifying the general topics discussed in Arabic unvowelized documents. The proposed topic detection system of Arabic texts is based on Mutual Information for Topic Oriented Vocabulary (TOV) and classification according to Jaccard and adapted TF-IDF indicators. The experimental results are presented in terms of precision, recall and F1 measure evaluating the influence of factors such as: vocabulary length and morphological analysis on Arabic Topic Detection.

There has been an increase in the number of young millennial Balinese who are bilinguals showing a shift with high competency in Indonesian at the concomitant expense of their Balinese language competency and related indigenous knowledge. The project takes advantage of the momentum with the surge of the enthusiasm and needs for online learning in the current context of COVID-19. The project focuses on digital dictionary research and development, addressing a clear gap in this space of Balinese digital humanity to have a learning resource in the broader literacy context of culture and language preservation and education. The digital dictionary online design is expected to benefit Balinese learners and other parties, including academic communities in Bali and across the globe. The language digital dictionary is a crosslingual system to facilitate the translation of a source language to a target language based on keywords to query the translation. The use of keyword-based query for translation presents an ambiguity, which the use of ontology can help to minimise. The design, development, and evaluation of Balinese language dictionary ontology in this study was done in consultation with Balinese language experts.

De nombreuses tâches medicales, telles que l’auto-diagnostic et le recrutement de patients pour des essais cliniques, impliquent l’utilisation d’outils d’acces a l’information. Une etape cle de ces tâches repose sur l’appariement entre documents dont l’enjeu majeur est de reduire le fosse semantique entre les representations de l’information brute des documents et l’interpretation issue d’experts medicaux. Guides par les avancees recentes sur les approches neuronales, nous proposons un modele d’apprentissage de representation des documents permettant de capturer a la fois la semantique des concepts medicaux valides dans une ressource externe et la semantique issue des mots des documents. Notre modele est evalue experimentalement au travers de deux tâches de recherche d’information (RI) medicale differentes qui sont en l’occurrence la"RI liee a aide au diagnostic" et la "recherche clinique de cohortes"

De nombreux travaux en recherche d'information (RI) ont montre que l'utilisation des sources d'evidence provenant de ressources semantiques externes pourrait ameliorer la performance de l'appariement. Par ailleurs, les approches neuronales sont devenues des modeles de reference qui permettent de capturer a partir des corpus, la semantique latente des mots qui peut etre injectee dans les modeles RI. Ce papier presente un modele qui a pour but de reduire le fosse semantique en RI en combinant ces deux sources d'evidence. C'est un modele neuronal tripartite pour la representation semantique de documents qui exploite des connaissances expli-cites pour regulariser conjointement l'apprentissage de representations des mots, des concepts et des documents. Nous montrons l'efficacite de notre modele sur differentes tâches de RI.

Previous work in information retrieval have shown that using evidence, such as concepts and relations, from external knowledge sources could enhance the retrieval performance. Recently, deep neural approaches have emerged as state-of-the art models for capturing word semantics. This paper presents a new tri-partite neural document language framework that leverages explicit knowledge to jointly constrain word, concept, and document learning representations to tackle a number of issues including polysemy and granularity mismatch. We show the effectiveness of the framework in various IR tasks.

Ontologies are used to explicitly represent knowledge of a various domain, and thus provide a shared understanding. Therefore, with the explosion of textual information on the Internet they are becoming a key technology for semantic-driven modeling, knowledge interchange and integration. Islam is one of the most popular religions of the world and Quran and Sunnah is the main source of knowledge for Muslims. To utilize this non-trivial knowledge domain for the betterment of humanity, numerous studies have been carried out to exploit ontologies for capturing knowledge from Islamic knowledge sources. This paper presents a review of different ontology oriented approaches for building domain specific ontology for Islamic knowledge domain, with the goal to identify the main problems in ontology development, and shortcomings of these approaches.

Sign Language is a language that used by Deaf community. One of the most widely used SL is the American Sign Language. In order to investigate the communication between Deaf people and others among them in the community, a machine translation system should be available for them in free use. The development of machine translation system that translate an English text into Sign language needs a grammar that producing Sign language from an input English text. In this paper a proposed ASL grammar rules that used to covert English sentence into ASL sentence will be produced. The grammar rules have been introduced as an If-ThenGrammar.

This study focusses on defining a new variant of regulated grammars called multiset controlled grammars as well as investigating their computational power. In general, a multiset controlled grammar is a grammar equipped with an arithmetic expression over multisets terminals where to every production in the grammar a multiset is assigned, which represents the number of the occurrences of terminals on the right-hand side of the production. Then a derivation in the grammar is said to be successful if only if its multiset value satisfies a certain relational condition. In the study, we have found that control by multisets is powerful tool and yet a simple method in regulation of generative processes in grammars. We have shown that multiset controlled grammars are at least as powerful as additive valence grammars, and they are at most powerful as matrix grammars.

The development of Fasting Ontology in the Pillars of Islam is presented in this paper and has been built based on reliable sources of Islamic Knowledge. The METHONTOLOGY methodology is used for the ontology development, which include identifying motivation scenarios, creating the competency questions, implementation and evaluation. From the beginning of the development of life cycle, the ontology was appraised from the competency questions and the outcome were clear. Therefore, this ontology can link each concept specifically to the individual verse together with the Tafsir that is related to the topics. The ontology proposed will be part of a larger ontology on Five Pillars of Islam. This development of the ontology is intended to refer to the field of learning for other purpose. For instance, search engine, chatbot, expert system or knowledge-based system.

With the advancement of the web it is very difficult to keep up with the amplifying requirements of learning on web, to satisfy user's expectation. Users demand with the updated and accurate results. To solve the queries Search Engines use different techniques. Google the most famous search engine uses Page Ranking Algorithm. Ranking Algorithms arrange the results according to the user's needs. This paper deals with "Page Rank Algorithm". Our proposed algorithm is an extension of page rank algorithm which refines the results so that user gets what he/she expects. We have used a measure Average Precision to compare Page Rank algorithm and the proposed algorithm, and proved that our algorithm provides better results.

Web contents related to educational institutions as well as their geographic data of a country is an emerging field of data sharing and consolidating with suitable data repositories to extract useful information to improve and maintain the area-based quality of education. The information of these institutions is available in the unstructured or semi-structured format from heterogeneous sources on the web that originate challenges to develop a smarter method in finding specific information using traditional search engines. The integration of these heterogeneous data along with geographic information is a formidable task to explore implicit knowledge of educational institutions that assist people to improve these systems and it is still getting researchers' attention. In this regard, our research demonstrates the feasibility of semantic web technologies for converting and integrating these unstructured or semistructured information by introducing machine understandable description of resources and instances by consisting of their concepts and relations, called a repository name EduBD. This yields a magnificent knowledge graph with .75 million nodes, i.e. RDF triples to facilitate reasoning meaningful information by a graph based query language SPARQL. Furthermore, we utilized our knowledge-base EduBD with one more accessible spatial data source Geo-Bangladesh using Physical-Cyber-Social computing approach to examine spatial contents and social information of each institution and therefore achieved the semantic interoperability of our Linked Open Data (LOD) application by eliminating natural language polisemy problems.

In recent years in addition to operational databases, web databases have become an important data source for most of the organization’s. The web databases may be structured, semi-structured or unstructured such as files, HTML pages, etc. and contains several heterogeneity issues. Heterogeneity may be present in different forms, hence the information retrieval from heterogeneous data sources become a tedious task. As the number of sources increases, need more intelligent retrieval techniques. There are number of techniques are available to remove the heterogeneity but the main focus is on information content and semantics of the data. The use of semantic web technologies such as ontology helps to represent such web data into clear information which can be incorporated in a data Warehouse. Ontology also helps to represent the industry requirements in a prescribed way, which needs to be used during the design. This report presents an ontology driven methods which helps to integrate dat...

Ontologies are used to explicitly represent knowledge of a various domain, and thus provide a shared understanding. Therefore, with the explosion of textual information on the Internet they are becoming a key technology for semantic-driven modeling, knowledge interchange and integration. Islam is one of the most popular religions of the world and Quran and Sunnah is the main source of knowledge for Muslims. To utilize this non-trivial knowledge domain for the betterment of humanity, numerous studies have been carried out to exploit ontologies for capturing knowledge from Islamic knowledge sources. This paper presents a review of different ontology oriented approaches for building domain specific ontology for Islamic knowledge domain, with the goal to identify the main problems in ontology development, and shortcomings of these approaches.

A key challenge in current Business Analytics (BA) is the selection of suitable indicators for business objectives. This requires the exploration of business data through data-driven approaches, while modelling business strategies together with domain experts in order to represent domain knowledge. In particular, Key Performance Indicators (KPIs) allow human experts to properly model ambiguous enterprise goals by means of quantitative variables with numeric ranges and clear thresholds. Besides business-related domains, the usefulness of KPIs has been shown in multiple domains, such as: Education, Healthcare and Agriculture. However, finding accurate KPIs for a given strategic goal still remains a complex task, specially due to the discrepancy between domain assumptions and data facts. In this regard, the semantic web emerges as a powerful technology for knowledge representation and data modeling through explicit representation formats and standards such as RDF(S) and OWL. By using this technology, the semantic annotation of indicators of business objectives would enrich the strategic model obtained. With this motivation, an ontology-driven approach is proposed to formally conceptualize essential elements of indicators, covering: performance, results, measures, goals and relationships of a given business strategy. In this way, all the data involved in the selection and analysis of KPIs are then integrated and stored in common repositories, hence enabling sophisticated querying and reasoning for semantic validation. The proposed semantic model is evaluated on a real-world case study on water management. A series of data analysis and reasoning tasks are conducted to show how the ontological model is able to detect semantic conflicts in actual correlations of selected indicators.

This paper describes a work in constructing two models of knowledge representation (KR) in aiming to do evaluation of their achievement in contributing to increase performance of retrieving information on English Quran domain. Due to many approaches available to construct a KR in providing data for information retrieval process, there is a need to find out in what model the KR could provide a valuable contribution for retrieving information. We focused on ontology-based KR and graph database-based KR. We use Quranic Arabic corpus that available at http://www.corpus.quran.com as a source to build the KR. We extracted several data from it i.e. English token, token location, and token Part of Speech (POS). Protégé is used to construct the ontology and Neo4j is utilized in developing the graph database. Both KR models will be equipped in developing of an English Quran Question Answering system in order to evaluate their benefit.

A question answering system is a special type of information retrieval system [1] that retrieves relevant short answers that match the question, instead of retrieving relevant full documents in a standard information retrieval system. In this study, we use three prototypes uses different resources for answers: MS Access database in prototype1, text files in prototype2 and prototype3, for storing results, each of which is one verse (Ayah) from two chapters of the holy Quran: AlBagarah and AlFati'hah. Prototype1 uses an MS Access database and rule-based system for retrieving matching answers after removing stop words and diacritics from the input Arabic question. Prototype2 and Prototype3 use indexed text files and the Lucene search engine and its techniques, adapted to deal with our Arabic text corpus. These systems accept a question in natural language form, then search for the relevant answers from the text files. We evaluated the Prototypes with thirty questions about the Qura...

In recent years in addition to operational databases, web databases have become an important data source for most of the organization’s. The web databases may be structured, semi-structured or unstructured such as files, HTML pages, etc. and contains several heterogeneity issues. Heterogeneity may be present in different forms, hence the information retrieval from heterogeneous data sources become a tedious task. As the number of sources increases, need more intelligent retrieval techniques. There are number of techniques are available to remove the heterogeneity but the main focus is on information content and semantics of the data. The use of semantic web technologies such as ontology helps to represent such web data into clear information which can be incorporated in a data Warehouse. Ontology also helps to represent the industry requirements in a prescribed way, which needs to be used during the design. This report presents an ontology driven methods which helps to integrate dat...

Plagiarism has become one of the most concerned problems since there are several kinds of plagiarism that are hard to detect. Extrinsic plagiarism is now being handled well, but intrinsic plagiarism is not. Intrinsic plagiarism detection is being distracted by the mixed up structure and the using of another word which have the same meaning. Several methods have been research to handle this problem, not only using the pattern reading but also parsing the sentences, but still couldn't give one more accurate way to detect it. In this research, we propose to use Natural Language Processing (NLP) to create the new way to detect plagiarism. Begin with using syntactic parsing method to parse the suspicious document and find the list of words which have the same meaning with it while considering the Part-Of-Speech (POS) element of that word (semantic parsing). This algorithm also includes creating the new structure of the object before comparing them. The result of this research present...

This paper describes a work in constructing two models of knowledge representation (KR) in aiming to do evaluation of their achievement in contributing to increase performance of retrieving information on English Quran domain. Due to many approaches available to construct a KR in providing data for information retrieval process, there is a need to find out in what model the KR could provide a valuable contribution for retrieving information. We focused on ontology-based KR and graph database-based KR. We use Quranic Arabic corpus that available at http://www.corpus.quran.com as a source to build the KR. We extracted several data from it i.e. English token, token location, and token Part of Speech (POS). Protégé is used to construct the ontology and Neo4j is utilized in developing the graph database. Both KR models will be equipped in developing of an English Quran Question Answering system in order to evaluate their benefit.

This paper presents a work in developing a semantic-based question answering system (QAS) for Indonesian Translation of Quran (ITQ). This research is motivated by the lacks of previous built QAS that caused by a keyword-based retrieval. Instead of keeping the retrieval method, we shifted to a semantic approach where the retrieval process is done by using a semantic similarity measurement. In doing so, we built an ontology of ITQ to get the concepts as well as verses where they appear in. We applied three factoid question types on the QAS that including Who, Where, and When. Furthermore, a weighted vector for each concept that belongs to respective expected answering type (also called as named entity group) i.e. Person, Location, and Time is generated in order to feed semantic interpreter on user question. From 222 concepts defined from the ontology, we clustered them into 77, 24, and 6 concepts for Person, Location, and Time respectively. Since we found there are some characteristics of texts in ITQ, we developed our own modules to deal with including generate the inverted index and named entity recognition. Answer extraction is conducted by applying some features extraction in order to score the answer candidates. Evaluation of the system is designed by providing two data set of question and answer where the first one is purposed to measure the effectiveness of semantic approach comparing with keyword-based retrieval and the last one aims to know system performance in regard the appearance of concepts in ITQ.