Entity-relationship diagram generation with natural language processing and machine learning approach

Basit Öğe Kaydı
dc.authorid0000-0002-8944-5449
dc.contributor.advisorEkin, Emineen_US
dc.contributor.authorKöprülü, Mertalien_US
dc.contributor.otherIşık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programıen_US
dc.date.accessioned2023-08-29T11:25:40Z
dc.date.available2023-08-29T11:25:40Z
dc.date.issued2023-08-24
dc.departmentIşık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programıen_US
dc.descriptionText in English ; Abstract: English and Turkishen_US
dc.descriptionIncludes bibliographical references (leaves 71-72)en_US
dc.descriptionxi, 73 leavesen_US
dc.description.abstractAs software systems continue to grow in complexity, the need for efficient and accurate design methodologies becomes increasingly critical. Entity-Relationship Diagrams (ERDs) provide a powerful visual representation of system structures and dependencies, serving as a foundation for software engineering and database design. However, manually creating ERDs from textual requirements is time-consuming and manual. To address this challenge, this research explores the application of natural language processing (NLP) techniques to automatically extract relevant information from unstructured text and generate ERDs. The proposed approach leverages the strengths of rule-based techniques, semantic analysis, and machine learning algorithms to automatically identify entities, attributes, relationships, and cardinalities from natural language input. Our study offers practical insights into the utilization of linguistic and semantic analysis, and machine learning for efficient information extraction. The proposed system aims to streamline the ERD creation process and improve the accuracy and quality of the resulting diagrams. While the proposed approach shows promising results, the limitations in heuristic rule coverage and data dependencies are acknowledge. Furthermore, the evaluation results demonstrate in detecting entities, attributes, and relations, with f1-scores of 0.96, 0.93, and 0.92, and resolving the components specifications achieved accuracy of 0.87, 0.84, 0.91, respectively. The findings contribute to advancing ERD extraction from text and suggest future research directions for improving the robustness and usability of the solution. The fusion of NLP techniques with ERD creation highlights the potential for enhancing the software development lifecycle and opens new avenues for research in the realm of information extraction from natural language text.en_US
dc.description.abstractYazılım sistemleri giderek karmaşıklık kazandıkça, verimli ve doğru tasarım yöntemlerine olan ihtiyaç artan bir şekilde kritik hale gelmektedir. Varlık İlişki Diyagramları (ERD), sistem yapılarını ve bağımlılıklarını güçlü bir görsel diyagram ile sunarak yazılım mühendisliği ve dahi veri tabanı tasarımının temelini oluştururlar. Ancak, metinsel gereksinimlerden ERD'lerin el ile oluşturulması zaman alıcı ve zahmet gerektirir iken, tasarım yapan kişinin öznel eleştirisine bağlıdır. Bu zorluğun üstesinden gelmek için bu tez, doğal dil işleme (NLP) tekniklerinin kullanımını ve metinden diyagram ile ilgili gerekli olan bilgileri otomatik olarak çıkarmak ve ERD'ler oluşturmak için incelemektedir. Önerilen bu yaklaşım, doğal dil girdilerinden varlık, varlıkların özniteliklerini ve ilişkilerini ve kardinalitelerini otomatik olarak belirlemek için kural tabanlı tekniklerin, anlamsal analizin ve makine öğrenimi algoritmalarının birleşimini kullanır. Bu çalışma, dilbilimsel ve anlamsal analiz ile makine öğreniminin verimli bilgi çıkarımı için kullanılmasına ilişkin araştırmaları sunarak deneyler yapar ve bu deney sonuçlarını karşılaştırması sonucu önerilen yöntemin eksikliklerini ve güçlü yönlerini bildirir. Önerilen bu sistem, ERD oluşturma sürecini basitleştirmeyi ve bilgi çıkarımı ile ERD’lerin doğru ve kaliteli üretimini amaçlar. Ek olarak, bu değerlendirme, varlık, öznitelik ve ilişkilerin tespitinde sırasıyla 0.96, 0.93 ve 0.92 f1 puanı almış, bileşen özelliklerinin çözümlenmesinde ise doğru diyagram varlıklarının özelliklerini bulmada sırasıyla 0.87, 0.84 ve 0.91 doğruluk oranını elde etmiştir. Elde edilen bu bulgular, metinden ERD çıkarma konusunda ilerlemeye katkı sağlayıp ve dahi çözümün sağlamlığını ve kullanılabilirliğini artırmak için gelecekteki araştırmalar için yönergeler ve çözümler önerir. NLP tekniklerinin ERD oluşturma ile birleştirilmesi ve yazılım geliştirme yaşam döngüsünü geliştirmenin potansiyelini vurgulayarak metinden bilgi çıkarma alanına da yeni araştırma olanakları sunar.en_US
dc.description.tableofcontentsOVERVIEW OF ENTITY RELATIONSHIP DIAGRAMSen_US
dc.description.tableofcontentsDatabase Modellingen_US
dc.description.tableofcontentsEntity-Relationship Diagramsen_US
dc.description.tableofcontentsComponents of Entity Relationship Diagramen_US
dc.description.tableofcontentsEntityen_US
dc.description.tableofcontentsWeak Entityen_US
dc.description.tableofcontentsAttributeen_US
dc.description.tableofcontentsKey Attributeen_US
dc.description.tableofcontentsDerived Attributeen_US
dc.description.tableofcontentsMulti-Valued Attributeen_US
dc.description.tableofcontentsComposite Attributeen_US
dc.description.tableofcontentsRelationshipen_US
dc.description.tableofcontentsIdentifying Relationshipen_US
dc.description.tableofcontentsCardinalitiesen_US
dc.description.tableofcontentsRule-Based Approaches on Diagram Generationen_US
dc.description.tableofcontentsSemantic-Based Approachesen_US
dc.description.tableofcontentsMachine-Learning Approachen_US
dc.description.tableofcontentsPre-Processing Moduleen_US
dc.description.tableofcontentsSentence Segmentationen_US
dc.description.tableofcontentsWord Correction (Optional)en_US
dc.description.tableofcontentsTokenizationen_US
dc.description.tableofcontentsChunkingen_US
dc.description.tableofcontentsPart-Of-Speech Taggingen_US
dc.description.tableofcontentsWordnet Synonym Extractionen_US
dc.description.tableofcontentsWord Dependencyen_US
dc.description.tableofcontentsCustom Named Entity Extraction Moduleen_US
dc.description.tableofcontentsDependency Extractionen_US
dc.description.tableofcontentsCandidate Component Extractionen_US
dc.description.tableofcontentsVectorizationen_US
dc.description.tableofcontentsCustom Named Entity Recognizeren_US
dc.description.tableofcontentsComponent Feature Extraction Moduleen_US
dc.description.tableofcontentsSpecification Resolveren_US
dc.description.tableofcontentsComponent Taggingen_US
dc.description.tableofcontentsReduction of Redundant Informationen_US
dc.description.tableofcontentsGraph Pre – Processingen_US
dc.description.tableofcontentsExperimental Results of Custom Named Entity Recognition Moduleen_US
dc.description.tableofcontentsModel Case Outputsen_US
dc.description.tableofcontentsCase 1: "Attribute" of "Entity" Extractionen_US
dc.description.tableofcontentsCase 2: Relation Extractionen_US
dc.description.tableofcontentsCase 3: "Attribute" of "Relation" Extractionen_US
dc.description.tableofcontentsCase 4: Complex Relationsen_US
dc.description.tableofcontentsEvaluationen_US
dc.description.tableofcontentsConfusion Matricesen_US
dc.description.tableofcontentsSemantic Roles and Their Definitionsen_US
dc.description.tableofcontentsApproaches of Relation Extraction from Texten_US
dc.description.tableofcontentsUniversal Part-of-Speech Tagsen_US
dc.description.tableofcontentsSpacy Dependency Labelsen_US
dc.description.tableofcontentsSpacy Token Featuresen_US
dc.description.tableofcontentsSample of Component Relation Structureen_US
dc.description.tableofcontentsBi-Directional Long Short-Term Memory Network Feature Comparison for Custom Named Entity Recognitionen_US
dc.description.tableofcontentsConfusion Matrix of Entity Extractionen_US
dc.description.tableofcontentsConfusion Matrix of Attribute Extractionen_US
dc.description.tableofcontentsConfusion Matrix of Key Attribute Extractionen_US
dc.description.tableofcontentsConfusion Matrix of Relation Extractionen_US
dc.description.tableofcontentsEntity Shapeen_US
dc.description.tableofcontentsWeak Entity Shapeen_US
dc.description.tableofcontentsAttribute Shapeen_US
dc.description.tableofcontentsKey Attribute Shapeen_US
dc.description.tableofcontentsDerived Attribute Shapeen_US
dc.description.tableofcontentsMulti-Valued Attribute Shapeen_US
dc.description.tableofcontentsComposite Attribute Shapeen_US
dc.description.tableofcontentsRelationship Shapeen_US
dc.description.tableofcontentsIdentifying Relationship Shapeen_US
dc.description.tableofcontentsCardinality Ratio one-to-many, E1: E2 on Relation Ren_US
dc.description.tableofcontentsProposed Model of Habiben_US
dc.description.tableofcontentsParser tree of the sentence “X hit the ball.”en_US
dc.description.tableofcontentsApproach of S. Btoushen_US
dc.description.tableofcontentsERD Modeling Generation Frameworken_US
dc.description.tableofcontentsBlock diagram of large-scale Object-Based Language Interactoren_US
dc.description.tableofcontentsIllustration of Semantic Neten_US
dc.description.tableofcontentsModel of ER-Converter Toolen_US
dc.description.tableofcontentsMachine Learning Model of Kashmiraen_US
dc.description.tableofcontentsAnnotated Data output of Kashmiraen_US
dc.description.tableofcontentsProposed Modelen_US
dc.description.tableofcontentsProposed System Architectureen_US
dc.description.tableofcontentsPre-processing Moduleen_US
dc.description.tableofcontentsDependency Output of Given Sentenceen_US
dc.description.tableofcontentsExample Dependency Treeen_US
dc.description.tableofcontentsCustom Named Entity Extraction Moduleen_US
dc.description.tableofcontentsDefault Named Entity Recognizer output of SpaCyen_US
dc.description.tableofcontentsRecurrent Neural Network Cell Structureen_US
dc.description.tableofcontentsExample Usage of RNN in NERen_US
dc.description.tableofcontentsLong-Short Term Memory Cell Structureen_US
dc.description.tableofcontentsBi-directional LSTM Architectureen_US
dc.description.tableofcontentsComponent Feature Extraction Moduleen_US
dc.description.tableofcontentsIllustration of dependency tree of 5th sentenceen_US
dc.description.tableofcontentsGraph Pre-Processing Moduleen_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 1en_US
dc.description.tableofcontentsIllustration of Elmasri on Scenario 1en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 2 (a), ERD illustration (b)en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 3en_US
dc.description.tableofcontentsElmasri Illustration on Scenario 3en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 4en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 5en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 6en_US
dc.description.tableofcontentsDependency Tree Illustration of sentence: “Suppliers, Parts, and Projects have ternary relation called ‘supply’ which has quantity attribute.”en_US
dc.description.tableofcontentsSolution Entity Relationship Diagram of Scenario 7en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 7en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 8en_US
dc.description.tableofcontentsGenerated Entity Relationship Diagram of Scenario 9en_US
dc.identifier.citationKöprülü, M. (2023). Entity-relationship diagram generation with natural language processing and machine learning approach. İstanbul: Işık Üniversitesi Lisansüstü Eğitim Enstitüsü.en_US
dc.identifier.urihttps://hdl.handle.net/11729/5691
dc.institutionauthorKöprülü, Mertalien_US
dc.institutionauthorid0000-0002-8944-5449
dc.language.isoenen_US
dc.publisherIşık Üniversitesien_US
dc.relation.publicationcategoryTezen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectEntity-relationship diagramen_US
dc.subjectNatural language processingen_US
dc.subjectNamed entity recognitionen_US
dc.subjectInformation extractionen_US
dc.subjectVarlık-ilişki diyagramıen_US
dc.subjectDoğal dil işlemeen_US
dc.subjectAdlandırılmış varlık tanımaen_US
dc.subjectBilgi çıkarımıen_US
dc.subject.lccQA76.9.N38 K67 2023
dc.subject.lcshMachine learning.en_US
dc.subject.lcshNatural language processing.en_US
dc.subject.lcshNatural language processing (Computer science).en_US
dc.subject.lcshEntity-relationship modeling.en_US
dc.titleEntity-relationship diagram generation with natural language processing and machine learning approachen_US
dc.title.alternativeDoğal dil işleme ve makine öğrenmesi yaklaşımıyla varlık-ilişki diyagram üretimien_US
dc.typeMaster Thesisen_US
dspace.entity.typePublication

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Entity_relationship_diagram_generation_with_natural_language_processing_and_machine_learning_approach.pdf
Boyut:
2.14 MB
Biçim:
Adobe Portable Document Format
Açıklama:
MasterThesis
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Lisansüstü Eğitim Enstitüsü Tez Koleksiyonu