AUTOMATIC ONTOLOGY CONSTRUCTION IN FICTION-BASED DOMAIN

2011 ◽  
Vol 21 (08) ◽  
pp. 1147-1167 ◽  
Author(s):  
HUI-NGO GOH ◽  
CHING-CHIEH KIU ◽  
LAY-KI SOON ◽  
BALI RANAIVO-MALANÇON
Keyword(s):  
Domain Knowledge ◽  
Threshold Value ◽  
New Techniques ◽  
Ontology Construction ◽  
Non Fiction ◽  
Algorithmic Framework

The field of ontology has received attention lately due to the increasing needs in conceptualizing the domain knowledge for resolving various jobs' demand. Numerous new techniques, tools and applications have then been developed for their suitability in managing knowledge. However, most works carried out focused on non-fiction domain and categorizing the concepts into component or cluster. Hence, the originality of the content flow is not preserved. This paper presents an automated ontology construction in fiction domain. The significance of the study lies in (1) designing a simple and easy algorithmic framework for automated ontology construction while preserving the originality of the content flow in an ontology, (2) identification of suitable threshold value in extracting true terms, and (3) process an unstructured fiction-based domain text into meaningful structure automatically.

Human-centric Faceted Approach for Ontology Construction

2020 ◽  
Vol 47 (1) ◽  
pp. 31-44
Author(s):  
Shiv Shakti Ghosh ◽  
Subhashis Das ◽  
Sunil Kumar Chatterjee
Keyword(s):  
Domain Knowledge ◽  
Information Science ◽  
Library And Information Science ◽  
Construction Process ◽  
Information Need ◽  
Ontology Construction ◽  
System P ◽  
Facet Analysis ◽  
Tourism Information ◽  
Selective Dissemination Of Information

In this paper, we propose an ontology building method, called human-centric faceted approach for ontology construction (HCFOC). HCFOC uses the human-centric approach, improvised with the idea of selective dissemination of information (SDI), to deal with context. Further, this ontology construction process makes use of facet analysis and an analytico-synthetic classification approach. This novel fusion contributes to the originality of HCFOC and distinguishes it from other existing ontology construction methodologies. Based on HCFOC, an ontology of the tourism domain has been designed using the Protégé-5.5.0 ontology editor. The HCFOC methodology has provided the necessary flexibility, extensibility, robustness and has facilitated the capturing of background knowledge. It models the tourism ontology in such a way that it is able to deal with the context of a tourist’s information need with precision. This is evident from the result that more than 90% of the user’s queries were successfully met. The use of domain knowledge and techniques from both library and information science and computer science has helped in the realization of the desired purpose of this ontology construction process. It is envisaged that HCFOC will have implications for ontology developers. The demonstrated tourism ontology can support any tourism information retrieval system.

scholarly journals Multi-label classification of research articles using Word2Vec and identification of similarity threshold

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ghulam Mustafa ◽  
Muhammad Usman ◽  
Lisu Yu ◽  
Muhammad Tanvir afzal ◽  
Muhammad Sulaiman ◽  
...  
Keyword(s):  
Digital Libraries ◽  
Domain Knowledge ◽  
Contextual Information ◽  
Threshold Value ◽  
Suggested Approach ◽  
General Terms ◽  
Statistical Measures ◽  
Current State ◽  
Average Accuracy ◽  
Domain Expertise

AbstractEvery year, around 28,100 journals publish 2.5 million research publications. Search engines, digital libraries, and citation indexes are used extensively to search these publications. When a user submits a query, it generates a large number of documents among which just a few are relevant. Due to inadequate indexing, the resultant documents are largely unstructured. Publicly known systems mostly index the research papers using keywords rather than using subject hierarchy. Numerous methods reported for performing single-label classification (SLC) or multi-label classification (MLC) are based on content and metadata features. Content-based techniques offer higher outcomes due to the extreme richness of features. But the drawback of content-based techniques is the unavailability of full text in most cases. The use of metadata-based parameters, such as title, keywords, and general terms, acts as an alternative to content. However, existing metadata-based techniques indicate low accuracy due to the use of traditional statistical measures to express textual properties in quantitative form, such as BOW, TF, and TFIDF. These measures may not establish the semantic context of the words. The existing MLC techniques require a specified threshold value to map articles into predetermined categories for which domain knowledge is necessary. The objective of this paper is to get over the limitations of SLC and MLC techniques. To capture the semantic and contextual information of words, the suggested approach leverages the Word2Vec paradigm for textual representation. The suggested model determines threshold values using rigorous data analysis, obviating the necessity for domain expertise. Experimentation is carried out on two datasets from the field of computer science (JUCS and ACM). In comparison to current state-of-the-art methodologies, the proposed model performed well. Experiments yielded average accuracy of 0.86 and 0.84 for JUCS and ACM for SLC, and 0.81 and 0.80 for JUCS and ACM for MLC. On both datasets, the proposed SLC model improved the accuracy up to 4%, while the proposed MLC model increased the accuracy up to 3%.

State of the Art Recommendation Approaches

2020 ◽  
pp. 1621-1651
Author(s):  
Bhupesh Rawat ◽  
Sanjay K. Dwivedi
Keyword(s):  
Recommender Systems ◽  
Domain Knowledge ◽  
Information Overload ◽  
State Of The Art ◽  
New Techniques ◽  
Contextual Data ◽  
Additional Information ◽  
E Learning ◽  
Traditional Approaches

Recommender systems have been used successfully in order to deal with information overload problems in a wide variety of domains ranging from e-commerce, e-tourism, to e-learning. They typically predict the ratings of unseen items by a user and recommend the top N items based on user's profile. Moreover, the profile can be enriched further by using additional information such as contextual data, domain knowledge, and tagging information among others for improving the quality of recommendations. Traditional approaches have not been effective in exploiting these additional data sources. Hence, new techniques need to be developed for extracting and integrating them into the recommendation process. In this article, the authors present a survey on state of the art recommendation approaches their algorithms, issues and also provides further research directions for developing smart and intelligent recommender systems.

Knowware-Based Software Engineering

2014 ◽  
pp. 567-596
Author(s):  
RuQian Lu ◽  
Zhi Jin
Keyword(s):  
Software Engineering ◽  
Domain Knowledge ◽  
Web Search ◽  
Knowledge Modeling ◽  
New Techniques ◽  
J2ee Platform ◽  
The Third ◽  
Knowledge Based ◽  
Basic Concepts ◽  
Further Development

The first part of this chapter reviews the origin of knowware-based software engineering. It originates from the authors' experiences in finding new techniques for knowledge-based software engineering while performing PROMIS, a continuing project series from the 1990s. The key point of PROMIS is to generate applications automatically by separating the development of domain knowledge from that of software architecture, with an important innovation of acquiring and summarizing domain knowledge automatically based on the pseudo-natural language understanding techniques. However, during PROMIS development, the authors did not find an appropriate form for the separated domain knowledge. The second part of the chapter briefly describes how the authors came to the concept of knowware. They stated that the essence of knowware is its capacity as a commercialized form of domain knowledge. It is also the third major component of IT after hardware and software. The third part of the chapter introduces the basic concepts of knowware and knowware engineering. Three life cycle models of knowware engineering and the design of corresponding knowware implementations are given. The fourth part of the chapter introduces object-oriented mixware engineering. In the fifth part of the chapter, two recent applications of knowware technique regarding smart room and Web search are reported. As a further development of PROMIS, the sixth part of the chapter discusses knowware-based redesign of its framework. In the seventh part of the chapter, the authors discuss automatic application generation and domain knowledge modeling on the J2EE platform, which combines techniques of PROMIS, knowware, and J2EE, and the development and deployment framework (i.e. PROMIS/KW**).

The Reflexive Practitioner

2012 ◽  
pp. 135-148
Author(s):  
Stephen Dobson
Keyword(s):  
Action Research ◽  
Collaborative Research ◽  
Domain Knowledge ◽  
Critical Reflection ◽  
Formal Ontology ◽  
Research Setting ◽  
Ontology Construction ◽  
Planning Strategies

This chapter aims to set out relevant discourse and approaches to consider when planning strategies for acquiring and building knowledge for formal ontology construction. Action Research (AR) is offered as a key means to help structure the necessary reflexivity required to enrich the researcher’s understanding of how they know what they know, particularly within a collaborative research setting. This is especially necessary when revealing tacit domain knowledge through participation with actors and stakeholders: “In this kind of research it is permissible to be openly normative and to strive for change, but not to neglect critical reflection” (Elfors & Svane 2008, 1).

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

2017 ◽  
Vol 10 (2) ◽  
pp. 59 ◽  
Author(s):  
Denis Eka Cahyani ◽  
Ito Wasito
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Design Patterns ◽  
Domain Knowledge ◽  
Expert Knowledge ◽  
Relation Extraction ◽  
Ontology Construction ◽  
Text Corpora ◽  
Ontology Design ◽  
Fully Automatic

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.

scholarly journals Supervised Health Stage Prediction Using Convolutional Neural Networks for Bearing Wear

Sensors ◽  
2020 ◽  
Vol 20 (20) ◽  
pp. 5846
Author(s):  
Sungho Suh ◽  
Joel Jang ◽  
Seungjae Won ◽  
Mayank Shekhar Jha ◽  
Yong Oh Lee
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Domain Knowledge ◽  
Time Series Data ◽  
Graphical Representation ◽  
Ground Truth ◽  
Threshold Value ◽  
Series Data ◽  
Health State ◽  
Feature Extraction Method

Early detection of faults in rotating machinery systems is crucial in preventing system failure, increasing safety, and reducing maintenance costs. Current methods of fault detection suffer from the lack of efficient feature extraction method, the need for designating a threshold producing minimal false alarm rates, and the need for expert domain knowledge, which is costly. In this paper, we propose a novel data-driven health division method based on convolutional neural networks using a graphical representation of time series data, called a nested scatter plot. The proposed method trains the model with a small amount of labeled data and does not require a threshold value to predict the health state of rotary machines. Notwithstanding the lack of datasets that show the ground truth of health stages, our experiments with two open datasets of run-to-failure bearing demonstrated that our method is able to detect the early symptoms of bearing wear earlier and more efficiently than other threshold-based health indicator methods.

Knowware-Based Software Engineering

2017 ◽  
pp. 293-323
Author(s):  
RuQian Lu ◽  
Zhi Jin
Keyword(s):  
Software Engineering ◽  
Domain Knowledge ◽  
Web Search ◽  
Knowledge Modeling ◽  
New Techniques ◽  
J2ee Platform ◽  
The Third ◽  
Knowledge Based ◽  
Basic Concepts ◽  
Further Development

The first part of this chapter reviews the origin of knowware-based software engineering. It originates from the authors' experiences in finding new techniques for knowledge-based software engineering while performing PROMIS, a continuing project series from the 1990s. The key point of PROMIS is to generate applications automatically by separating the development of domain knowledge from that of software architecture, with an important innovation of acquiring and summarizing domain knowledge automatically based on the pseudo-natural language understanding techniques. However, during PROMIS development, the authors did not find an appropriate form for the separated domain knowledge. The second part of the chapter briefly describes how the authors came to the concept of knowware. They stated that the essence of knowware is its capacity as a commercialized form of domain knowledge. It is also the third major component of IT after hardware and software. The third part of the chapter introduces the basic concepts of knowware and knowware engineering. Three life cycle models of knowware engineering and the design of corresponding knowware implementations are given. The fourth part of the chapter introduces object-oriented mixware engineering. In the fifth part of the chapter, two recent applications of knowware technique regarding smart room and Web search are reported. As a further development of PROMIS, the sixth part of the chapter discusses knowware-based redesign of its framework. In the seventh part of the chapter, the authors discuss automatic application generation and domain knowledge modeling on the J2EE platform, which combines techniques of PROMIS, knowware, and J2EE, and the development and deployment framework (i.e. PROMIS/KW**).

State of the Art Recommendation Approaches

2018 ◽  
Vol 10 (1) ◽  
pp. 51-76
Author(s):  
Bhupesh Rawat ◽  
Sanjay K. Dwivedi
Keyword(s):  
Recommender Systems ◽  
Domain Knowledge ◽  
Information Overload ◽  
State Of The Art ◽  
New Techniques ◽  
Contextual Data ◽  
Additional Information ◽  
E Learning ◽  
Traditional Approaches

Recommender systems have been used successfully in order to deal with information overload problems in a wide variety of domains ranging from e-commerce, e-tourism, to e-learning. They typically predict the ratings of unseen items by a user and recommend the top N items based on user's profile. Moreover, the profile can be enriched further by using additional information such as contextual data, domain knowledge, and tagging information among others for improving the quality of recommendations. Traditional approaches have not been effective in exploiting these additional data sources. Hence, new techniques need to be developed for extracting and integrating them into the recommendation process. In this article, the authors present a survey on state of the art recommendation approaches their algorithms, issues and also provides further research directions for developing smart and intelligent recommender systems.

Sign in / Sign up

Export Citation Format

Share Document