[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122024-en":3,"doc-seo-122024-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122024,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Knowledge and Learning - Synergies between Ontologies and Machine Learning - Doctoral Thesis","The growing pool of information and knowledge makes suitable knowledge representation indispensable. Over recent decades, ontologies have provided flexible descriptions with rich semantics, yet ontology engineering remains labor-intensive and time-consuming because it depends on consensus-building among many experts. Machine learning can enhance results but often faces transparency limitations. This thesis investigates synergies between ontologies and machine learning to extend ontologies and to integrate ontology-driven knowledge into learning tasks, including case studies on the ChEBI ontology.","Knowledge and Learning  \nSynergies between Ontologies and Machine Learning  \nDISS ERTAT IO N  \nzur Erlangung des akademischen Grades  \nDoktoringenieur (Dr. -Ing.)  \nangenommen durch die Fakultät für Informatik der Otto-von-Guericke-Universität Magdeburg  \nvon M.Sc. Martin Glauer  \n[geb. am](geb. am) 01.07.1989  \nGutachterinnen/Gutachter  \nProf. Dr. Till Mossakowski  \nProf. Dr. Robert Hoehndorf  \nProf. Dr. Janna Hastings  \nin Magdeburg  \nMagdeburg, den 10.10.2024  \nOtto-von-Guericke University Magdeburg  \nDepartment of Computer Science Institute for Intelligent Cooperating Systems  \nDoctoral Thesis  \nKnowledge and Learning  \nSynergies Between Ontologies and Machine Learning  \nAuthor:  \nMartin Glauer  \nOctober 10, 2024  \nAdvisers:  \nSupervisor  \nProf. Dr.-Ing. Till Mossakowski  \nDepartment of Computer Science Otto von Guericke University Universitätsplatz 2  \n39106 Magdeburg, Germany  \nSupervisor  \nProf. Dr. Janna Hastings  \nSchool of Medicine University of St.Gallen St.Jakob-Strasse 21 CH-9000 St.Gallen, Switzerland  \nGlauer, Martin:  \nKnowledge and Learning  \nSynergies Between Ontologies and Machine Learning Doctoral Thesis, Otto von Guericke University Magdeburg, 2024 .  \nContents  \nAbstract  \nZusammenfassung  \n1 Introduction and Motivation  \n1.1 Objectives of this Thesis ............................ 5  \n1.2 Structure of this Thesis ............................. 6  \n2 Background  \n2.1 Ontologies .................................... 7  \n2.2 ChEBI ....................................... 8  \n2.3 Cheminformatics ................................ 11  \n2.3.1 SMILES .................................. 11  \n2.3.2 Molecular Fingerprints ......................... 13  \n2.3.3 ClassyFire ................................ 15  \n2.4 Machine Learning ................................ 17  \n2.4.1 Logistic Regression ........................... 18  \n2.4.2 K-Nearest Neighbor .......................... 18  \n2.4.3 Decision Trees and Random Forests ................. 19  \n2.4.4 Naive Bayes ............................... 20  \n2.4.5 Linear Discriminant Analysis ..................... 21  \n2.4.6 Support Vector Machine ........................ 21  \n2.4.7 LSTM ................................... 22  \n2.4.8 Transformers and Electra ....................... 23  \n2.4.9 Binary Cross-Entropy Loss (BCE) ................... 27  \n2.4.10 Evaluation Metrics ........................... 28  \n3 Related Work  \n3.1 Ontology Learning ............................... 31  \n3.2 Chemical Ontologies and Structure-Based Classification of Chemicals 34  \n3.3 Machine Learning and Deep Learning Approaches ............ 35  \n3.4 Training with Semantic Support ....................... 38  \n4 Ontology Extension  \n4.1 Data preparation ................................ 43  \n4.1.1 A Balanced Approach ......................... 44  \n4.1.2 Lifting Data Limitations ........................ 46  \n4.1.3 Going Beyond ChEBI .......................... 49  \n4.2 Input Encodings ................................. 49  \n4.2.1 Fingerprints ............................... 50  \n4.2.2 Tokenization ............................... 50  \n4.3 Prediction Model ................................ 52  \n4.3.1 Traditional Approaches ........................ 52  \n4.3.2 Sequence-based models ........................ 53  \n4.4 Evaluation .................................... 55  \n4.4.1 Evaluation of the Traditional Methods and LSTM ......... 55  \n4.4.2 Evaluation of the Electra-based Models ............... 71  \n4.5 The ChEB-AI Tool ................................ 87  \n4.6 Chebifier ..................................... 89  \n4.6.1 The Chebifier System .......................... 89  \n4.6.2 User study ................................ 92  \n4.6.3 Results .................................. 94  \n4.7 Discussion .................................... 96  \n5 Semantic Support  \n5.1 Ontology Pre-Training ............................. 99  \n5.1.1 Datasets ................................. 102  \n5.1.2 Methods ................................. 103  \n5.","cbCaiv0zC6iXMZQQ","https://ap.wps.com/l/cbCaiv0zC6iXMZQQ","pdf",4638729,1,142,"English","en",105,"# Contents\n## 1 Introduction and Motivation\n## 2 Background\n## 3 Related Work\n## 4 Ontology Extension\n## 5 Semantic Support\n## 6 Conclusions and Future Work\n## A Bibliography","[{\"question\":\"What problem does the thesis address regarding ontologies and machine learning?\",\"answer\":\"Ontologies offer rich semantic knowledge representation but are expensive to develop, while machine learning can deliver strong results yet often lacks transparency. The thesis aims to combine both to mitigate these shortcomings.\"},{\"question\":\"How does the thesis propose to extend ontologies?\",\"answer\":\"It presents a novel machine-learning-based approach that extends ontologies using only an existing ontology and its annotations, evaluated with a case study on the ChEBI ontology.\"},{\"question\":\"How can ontologies support machine learning learning tasks in this thesis?\",\"answer\":\"The thesis provides methods to use ontologies in machine learning, including treating an ontology as a knowledge base even when relevant task knowledge is not explicitly represented, and introducing semantic support via ontology-based losses.\"}]","Knowledge and Learning - Synergies between Ontologies and Machine Learning - Doctoral Thesis | PDF",1785808348,358,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"knowledge-and-learning-synergies-between-ontologies-and-machine-learning-doctoral-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/knowledge-and-learning-synergies-between-ontologies-and-machine-learning-doctoral-thesis/122024/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address regarding ontologies and machine learning?","Question",{"text":75,"@type":76},"Ontologies offer rich semantic knowledge representation but are expensive to develop, while machine learning can deliver strong results yet often lacks transparency. The thesis aims to combine both to mitigate these shortcomings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis propose to extend ontologies?",{"text":80,"@type":76},"It presents a novel machine-learning-based approach that extends ontologies using only an existing ontology and its annotations, evaluated with a case study on the ChEBI ontology.",{"name":82,"@type":73,"acceptedAnswer":83},"How can ontologies support machine learning learning tasks in this thesis?",{"text":84,"@type":76},"The thesis provides methods to use ontologies in machine learning, including treating an ontology as a knowledge base even when relevant task knowledge is not explicitly represented, and introducing semantic support via ontology-based losses.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]