KAI Thesis Topics

You can find the slides presented at the MSc AI Thesis event here. Most of the topics below can be investigated by either BSc or MSc AI students. We also welcome groups of students working on the same or similar topic.

If you are interested in one of the projects below, please contact the supervisor(s) listed to receive more information about the topics. Where available, have a look at the detailed description first. Also, keep in mind that all theses can be shaped to accomodate your interests. Do note however that the KAI group has clear expectations of their students. We want to make sure students know what to expect from us as their supervisors. We have prepared a short document which touches upon some important points like meetings, planning and writing of your thesis.

The filter menu below can be used to limit the amount of projects on display. If you click on the keyword, only projects with that particular keyword are displayed. The number indicates the number of projects we have to offer with that keyword.

• Knowledge Extraction

  Knowledge Extraction aims at generating structured knowledge (knowledge graphs) from unstructured data (usually, text). These projects focus on the methods to extract knoweldge.

  • Information extraction from Structured lists ( Benno, B.Sc. )

    Benno Kruit (b.b.kruit@vu.nl) Many different kinds of documents contain lists because they are a simiple way of enumerating several related items. We want to investigate ways of extracting the information from the lists and retaining the inherent relationship between list items. (continue reading)
    • Wikipedia
    • NLP
    • Pattern learning

  • Detecting Entity-Attribute Tables in Wikipedia ( Benno, B.Sc. )

    Benno Kruit (b.b.kruit@vu.nl) Tables on web pages contain a wide variety of interesting information, which could be useful for web search or question answering applications. This projects aims to create a program that detects when each row of a table is about a different entity. (continue reading)
    • Wikipedia
    • Knowledge Graphs

  • Automated Processing of Scholarly CEUR-WS Data ( Ilaria, BSc./MSc. )

    Ilaria Tiddi (i.tiddi@vu.nl) The goal of this project is to support the automatisation of processing the CEUR-WS proceedings data. For a BSc thesis, the objective is to extract an ontology of CEUR knowledge. For a MSc thesis, this would be extended with analysing abstracts or creating an interface for data input and knowledge... (continue reading)
    • NLP
    • Knowledge Graphs
    • Machine Learning

  • Creating knowledge graphs for olfactory dysfunction and mental disorders ( Lise, MSc. )

    Lise Stork (l.stork@vu.nl) Biomedical text mining has emerged as a powerful tool to build up knowledge graphs and guide us through the vast plethora of available scientific literature and medical records. In this MSc. project, we primarily aim at the construction of a knowledge graph for the understanding of the link between olfactory... (continue reading)
    • Ontology Engineering
    • Knowledge Graphs
    • Bioinformatics
    • Machine Learning

  • Making research papers machine interpretable ( Lise, BSc./MSc. )

    Lise Stork (l.stork@vu.nl) The goal of this project is to see if we can partially automate or support the construction of knowledge graph on hypotheses from the literature. (continue reading)
    • Hybrid Intelligence
    • N-ary Relation Extraction
    • Promt Engineering

  • Automated Data-provenance Extraction ( Ritten, BSc./MSc. )

    Ritten Roothaert (h.m.roothaert@vu.nl) In a world where linked data and data-mining is omnipresent, determining which data was used for training a ML-model becomes increasingly more difficult and tedious. This project revolves around automating the process of extracting the provenance information of data used in a ML-pipeline. (continue reading)
    • LLM
    • Implementation
    • Data-mining
    • Machine Learning
    • Knowledge representation
    • Explainability

• Knowledge Graph Construction

  Knowledge Extraction aims at generating structured knowledge (knowledge graphs) from unstructured data (usually, text). These projects focus on the population task of a Knowledge Graph.

  • Detecting Entity-Attribute Tables in Wikipedia ( Benno, B.Sc. )

    Benno Kruit (b.b.kruit@vu.nl) System Dynamics models describe the behaviour of complex dynamical systems such as the climate. InsightMaker is a website for sharing such models. This project aims to formally describe the data sources of these models using RDF. (continue reading)
    • Dynamic Models
    • RDF

  • Benchmarks and Methods for understanding Narratives ( Ilaria, MSc. )

    Ilaria (i.tiddi@vu.nl) The project will look at using Knowledge Graphs to build and understand Narratives. (continue reading)
    • Explanations
    • Language Models
    • Knowledge Graphs

• Knowledge and Ontology Engineering

  These projects focus on the design, evolution and consomption of ontologies and ontology-based systems.

  • Knowledge Engineering for Hybrid Intelligence ( Ilaria, BSc./MSc. )

    Ilaria (i.tiddi@vu.nl) Inspired by Software Design and Engineering, Knowledge Engineering deals with the formal design, maintainance and usage of knowledge-based systems. In this project, we will look at modelling Hybrid Intelligent systems using knowledge engineering techniques. (continue reading)
    • Hybrid Intelligence
    • Knowledge Engineering
    • Ontology Engineering

  • Researching human-in-the-loop workflows for research assistants using Knowledge Graphs ( Lise, MSc. )

    Lise Stork (l.stork@vu.nl) The goal of this project is to research human-in-the-loop workflows for digital assistants for scientific discovery. (continue reading)
    • Knowledge Engineering
    • Knowledge Graphs
    • Hybrid Intelligence

  • SHACL-forms for publishing scientific findings ( Lise, MSc. )

    Lise Stork (l.stork@vu.nl) The goal of this project is to see if we can partially automate or support the construction of knowledge graph on hypotheses from the literature. (continue reading)
    • SHACL
    • Knowledge Graphs
    • Scientific Discovery

  • Community Detection from a Species Interaction Network ( Lise, BSc./MSc. )

    Lise Stork (l.stork@vu.nl) We will extract interesting communities in species interaction networks, or detect interesting logic rules that relate to these communitiess. (continue reading)
    • Rule Mining
    • Knowledge Graphs
    • Community Detection

  • ChImp 2.0: Extending Protege and its ability to provide change impact information (multiple projects) ( Romana, BSc./MSc. )

    Romana Pernisch (r.pernisch@vu.nl) The ChImp Protégé plugin helps ontology engineers during this process by summarising and displaying changes and the effects of changes on the ontology as a whole. We have multiple possible projects with ChImp. (continue reading)
    • Java
    • Protégé
    • Change Management
    • Ontology Engineering
    • User testing

  • Investigating Support for Ontology Evolution (multiple projects) ( Romana, BSc./MSc. )

    Romana Pernisch (r.pernisch@vu.nl) The process of ontology evolution is relatively long and complex. In your thesis you can investigate and compare tools for supporting this process or investigate automations options within this process. (continue reading)
    • Change Management
    • User Testing
    • Process Automation
    • Python
    • Java

  • Investigating the Impact of Changes on the Materialisation (multiple projects) ( Romana, BSc./MSc. )

    Romana Pernisch (r.pernisch@vu.nl) We have previously investigated the impact on the materialisation (making implicit knowledge explicit) and want to further the analysis by diving into more depth. This means that we want to investigate the types of changes in more detail but also the effect of the changes more localized in the materialisation,... (continue reading)
    • Change Management
    • Onology Materialisation
    • Ontologies
    • Knowledge representation

• Argument Mining

  These projects aim at finding argumentation structures from different types of data (structured, unstructured, semi-structured).

  • Orange3 Argument Mining Widget Based on a Formalism of Argumentation ( Atefeh, M.Sc. )

    Atefeh Keshavarzi (a.keshavarzi.zafarghandi@vu.nl) This project aims to bridge the gap between argumentation theory and data analysis and visualization by developing an argument mining widget for Orange3, an open-source data mining and machine learning software. (continue reading)
    • Computational argumentation
    • Argument mining
    • Orange3

  • Leveraging Argumentation Frameworks for Local Explainability of Black-Box Models ( Atefeh, M.Sc. )

    Atefeh Keshavarzi (a.keshavarzi.zafarghandi@vu.nl) This project aims to leverage the formalisms of argumentation to provide local explainability for black-box models, enabling non-experts to understand the reasons behind the system’s decisions. (continue reading)
    • Computational Argumentation
    • Machine Learning
    • Explainability

  • Explaining query answers in prioritized databases ( Loan, B.Sc./M.Sc. )

    Loan Ho (t.t.l.ho@vu.nl) This project aims to provide explanation of how the query answer was reached in consistent database. (continue reading)
    • Logic-Based Argumentation
    • Database Explanation
    • Explainable AI

  • Handling inconsistencies in argumentation knowledge ( Loan, B.Sc./M.Sc. )

    Loan Ho (t.t.l.ho@vu.nl) In the project, we will address inconsistencies in argumentation data by using logic-based reasoning. (continue reading)
    • Logic-Based Argumentation
    • Inconsistency Checking
    • Explainable AI

  • Computing extensions for argumentation with collective attacks ( Loan, B.Sc. )

    Loan Ho (t.t.l.ho@vu.nl) In this project, we will build a tool to calculate extensions for argumentation with collective attacks. The inputs are a set of arguments and collective attacks. The output returns different (stable, preferred, complete, grounded) extensions. (continue reading)
    • Logic-Based Argumentation
    • Java
    • Implementation

• Knowledge-based Robotics

  These projects look at how ontologies and knowledge graphs can support robotics applications.

  • Semantic mapping with a mobile service robot ( Mark, B.Sc./M.Sc. )

    Mark Adamik (m.adamik@vu.nl) In this project, you will be using the LoCoBot, a mobile robot equipped with multiple sensors. Your task would be to integrate object recognition methods (e.g. YOLO), path planning (SLAM) and knowledge representation & reasoning methods to solve planning problems. (continue reading)
    • Robotics
    • Computer Vision
    • Python
    • Robotic Operating System
    • Knowledge Representation
    • SLAM

  • Visual scene understanding for indoor mobile robots (with the use case of trash picking) ( Mark, B.Sc./M.Sc. )

    Mark Adamik (m.adamik@vu.nl) In this project, you will be using the LoCoBot, a mobile robot equipped with multiple sensors and a manipulator. Your task would be to integrate object recognition methods (e.g. YOLO) and knowledge representation & reasoning methods to solve pick and place problems representing trash collection. (continue reading)
    • Robotics
    • Computer Vision
    • Python
    • Robotic Operating System
    • Knowledge Representation
    • Machine Learning

  • Embodied Instructable Agents ( Ilaria, MSc. )

    Ilaria (i.tiddi@vu.nl) The goal of this project is to integrate a Reinforment Learning model trained for trajectory/segmentation learning on an embodied Hybrid Intelligent agent (a ROS-operting robot). (continue reading)
    • Hybrid Intelligence
    • Robotics
    • Reinforcement Learning

  • Energy-efficient robots through knowledge-awareness ( Ilaria, BSc./MSc. )

    Ilaria (i.tiddi@vu.nl) We have an ontology representing the capabilities of the robots (picking objects, moving, scanning surroundings, etc.). The ontology needs to be expanded with energy budgets so the robot can choose the actions to performed based on its capabilities and energy-efficiency. (continue reading)
    • Robotics
    • Knowledge Engineering
    • Hybrid Intelligence

  • Impact of ontology changes in robotic tasks ( Ilaria, BSc./MSc. )

    Ilaria (i.tiddi@vu.nl) Based on a robot operating with an ontology in the background, the goal here is to study how changes in such ontology can positively/negatively impact the tasks the robot has to perform. (continue reading)
    • Robotics
    • Knowledge Engineering
    • Ontology Evolution

  • Explaining Yolo Predictions with Argumentations ( Ilaria, BSc./MSc. )

    Ilaria (i.tiddi@vu.nl) The goal of this project is to explain the predictions of an object recognition model in the form of argumentations. (continue reading)
    • Robotics
    • Object Recognition

• Knowledge Graph-based Question Answering

  These projects focus on the Question Answering task over data structured in the form of KGs.

  • Information extraction from Structured lists ( Benno, B.Sc. )

    Benno Kruit (b.b.kruit@vu.nl) Twenty Questions is a popular parlor game where one player tries to guess what another player is thinking of, in less than 20 yes/no questions. This projects aims to create a program that asks these questions using a Knowledge Graph. (continue reading)
    • Wikipedia
    • Knowledge Graphs

  • Leveraging Large Language Models for Ontology Extraction through Question-Answering ( Jieying, B.Sc./M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This thesis explores automating ontology extraction using Large Language Models (LLMs). By leveraging LLMs' capabilities in context understanding and information extraction, this project aims to enable agile, real-time ontology development through a QA mechanism. (continue reading)
    • Ontology Extraction
    • LLM
    • Semantic Web
    • Knowledge Representation

  • Benchmarking Ontology Modularity and QA Using Real-world Ontologies ( Jieying, M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This project promotes modular ontologies for better maintenance and usability, alongside developing benchmarks for QA systems interacting with them. Incorporating real-world data is key to evaluating their practicality and scalability effectively. (continue reading)
    • Ontology Modularity
    • QA Systems
    • Benchmarks
    • Real-World Data
    • Knowledge Representation

  • Answering Research Questions over Data Cubes as SQA ( Lise, MSc. )

    Lise Stork (l.stork@vu.nl) Hypotheses generation and testing in scientific research is often a time-intensive process. This project revolves around making the process more reproducible and trustworthy, with the end goal of machine actionability – the ability of machines to discover knowledge with little human intervention. (continue reading)
    • Question Answering
    • Knowledge Graphs
    • Scientific Discovery

• Knowledge Graphs and Deep Learning

  These projects study how to deep learning models can capture different types of semantics represented in the data.

  • Incorporating Semantics in Message Passing methods ( Ilaria, MSc. )

    Ilaria (i.tiddi@vu.nl) We will look at feeding semantics in a message passing models such as R-GCN, and test it in a node labelling or link prediction scenario. (continue reading)
    • Deep Learning
    • Knowledge Engineering

  • Solving Math Word Problems with LLMs ( Ilaria, MSc. )

    Ilaria (i.tiddi@vu.nl) The project will look at creating a KG-based benchmark for solving Math World Problems. (continue reading)
    • Deep Learning
    • Knowledge Engineering

  • Enhancing Language Models with Ontology Subsumption Inference ( Jieying, M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This master's thesis aims to explore the potential of pre-trained language models for encoding and reasoning with complex ontology subsumptions, moving beyond simple relational knowledge bases to embrace sophisticated OWL ontologies. It seeks to enhance LMs' understanding and inference of concept subsumption relationships. (continue reading)
    • Language Models
    • Ontology Subsumption
    • Knowledge Representation
    • Inference Enhancement

  • Designing a Benchmark and Auto-Evaluator for Extracting Relevant Axioms from User Input ( Jieying, M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This project focuses on enhancing ontology extraction, a key component in semantic reasoning and knowledge base expansion. It addresses the challenges of processing vast, varied user-contributed content by proposing an innovative auto-evaluator. (continue reading)
    • Semantic Web
    • Data validation
    • Ontology Engineering

  • Extraction of Relevant Axioms Using Ontology Embedding ( Jieying, B.Sc./M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This project tackles the challenge of navigating large ontologies by extracting axioms most relevant to user interests. It aims to enhance usability and comprehension, making complex knowledge structures more accessible and digestible for human users, thereby improving interaction with vast knowledge domains. (continue reading)
    • Ontology Navigation
    • Axiom Extraction
    • Usability Enhancement
    • Knowledge Accessibility
    • Human-Computer Interaction

  • Ethnic AI: Bias Detection and Mitigation in Large Language Models ( Jieying, B.Sc./M.Sc. )

    Jieying Chen (j.chen2@vu.nl) Large Language Models (LLMs) are crucial for applications from information retrieval to content creation. The aim of this project is to use ontologies to benchmark LLM outputs against a standardized knowledge base, ensuring reliability, neutrality, and rectifying biases, enhancing LLM's ethical use and credibility. (continue reading)
    • Bias Detection
    • Ontologies
    • Knowledge Representation
    • LLM

  • Ontology Embedding using the BERT Model ( Jieying, B.Sc./M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This project explores embedding ontologies with the BERT model to enhance semantic web and intelligent systems, bridging symbolic and vector space representations. It aims to capture latent semantics, improving similarity computations and enabling richer downstream applications. (continue reading)
    • Ontology Embeddings
    • LLM
    • Semantic Web
    • Sub-symbolic AI

• Formal Logics, Modal Logics

  Projects looking into the application of differe kind of logics in AI (multi-agent) systems.

  • Possible applications of Alternating-time Temporal Epistemic Logic in AI ( Vera, BSc./MSc. )

    Vera Stebletsova (v.n.stebletsova@vu.nl) Different topics on applicing of Temporal Epistemic Logic in AI (continue reading)
    • Reasoning
    • Temporal Logics
    • Multi-Agent Systems

  • Doxastic Logic in AI ( Vera, BSc./MSc. )

    Vera Stebletsova (v.n.stebletsova@vu.nl) Different topics on Doxastic Logics (continue reading)
    • Reasoning
    • Doxastic Logics
    • Model Checking

  • Modeling Multi-Agent Systems with incomple information ( Vera, MSc. )

    Vera Stebletsova (v.n.stebletsova@vu.nl) We will look into the problem of modeling, analysis, and reasoning about systems with incomplete information. (continue reading)
    • Multi Agent Systems
    • Reasoning
    • Model Checking

  • Modal logic for AI ( Vera, MSc. )

    Vera Stebletsova (v.n.stebletsova@vu.nl) Finding an AI field for which you can construct a new applicable modal logic. (continue reading)
    • Modal Logics
    • Reasoning

• Ontologies and Reasoning

  These projects focus on reasoning over OWL or description logic-based ontologies.

  • Python-based Implementation of Ontology Modularity Tools ( Jieying, B.Sc./M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This project targets the development of swift, Python-based tools for ontology modularity. It focuses on creating accurate and efficient solutions for managing and updating large-scale knowledge representations. (continue reading)
    • Tool Development
    • Knowledge Representation
    • Computational Efficiency
    • Algorithm Optimization

  • Explaining Missing Entailments from Ontologies ( Patrick, M.Sc./B.Sc. )

    Patrick Koopmann (p.k.koopmann@vu.nl) In this project, you will develop methods for explaining missing entailments from ontologies. (continue reading)
    • Ontologies
    • Explainability
    • Reasoning
    • Logics
    • Description Logics

  • Explaining Entailments from Ontologies ( Patrick, M.Sc./B.Sc. )

    Patrick Koopmann (p.k.koopmann@vu.nl) In this project, you will investigate and develop alternative ways of explaining reasoning with ontologies. (continue reading)
    • Ontologies
    • Explainability
    • Reasoning
    • Logics
    • Description Logics

  • Automated Hypothesis Generation using ABox Abduction ( Patrick, B.Sc. )

    Patrick Koopmann (p.k.koopmann@vu.nl) This project is about generating, with the help of ontologies, hypotheses for unexpected observations. (continue reading)
    • Ontologies
    • Logics
    • Reasoning

  • Learning Concept Descriptions from Examples ( Patrick, M.Sc./B.Sc. )

    Patrick Koopmann (p.k.koopmann@vu.nl) In this project, you will use recent advancements on ontology reasoning to develop and evaluate a new method for learning conceptual (logic-based descriptions of groups of objects based on examples. (continue reading)
    • Ontologies
    • Learning
    • Reasoning
    • Logics
    • Description Logics

  • Extracting Sub-Ontologies ( Patrick, B.Sc. )

    Patrick Koopmann (p.k.koopmann@vu.nl) The aim of this project is to develop new heuristics to use existing tools that extract small parts from large ontologies. (continue reading)
    • Ontologies
    • Logics

  • Optimizing Concept Expressions ( Patrick, B.Sc. )

    Patrick Koopmann (p.k.koopmann@vu.nl) In this project, you will investigate how to automatically improve expressions found in an ontology. (continue reading)
    • Ontologies
    • Logics

• Information Extraction

  We offer multiple projects under the umbrella of information extraction with varying foci. Information extraction focuses on generating structured data from unstructured inputs in an automated manner. The input as well as the output can vary based on the application or end usage of the extracted data.

• Ontology Evolution

  Ontologies model specific domains. As domains evolve over time, ontologies have to be changed as well. Not only are the ontologies themsevels affected but also applications using those ontologies for various purposes. We have multiple theses in this domain.

• Hybrid Intelligence

• Argument and Rule Mining

  Rule mining, similarly to information extraction, aims at finding structures. In this case, we want to learn rules that describe the data best to help us understand it better. There are multiple projects that involve rule mining:

• Robotics and Knowledge Representation

  These projects look at the intersection of robotics and knowledge graphs. Knowledge of Robotic Operating System (ROS) is a plus:

• Explanations and Narratives

  The following topics are aimed at providing a more human-like AI, by creating explanations or creating narratives.

• Question Answering

  QA is a very broad topic. We, however, focus on QA over structured data in various forms:

• Multi-lingual problems

  Even though these topics would also fit under different topics already discribed above, we wanted to highlight them as they are both addressing the problem of multiple languages in different tasks:

• Semantics of Deep Learning Methods

• Systems of artificial intelligent agents

• Explanations for Ontologies

  We offer a range of projects around the topic of explanations for ontologies. We focus on ontologies based on description logics or OWL. A main advantage of formulating knowledge in such a formalism is that one can use a reasoner to derive implicit information. However, not always is the result of this reasoning process easy to understand: users might wonder why something was derived (explain positive entailment), or why something was not derived (explain negative entailments). Motivated by this, different methods have been developed to provide explanations for positive and negative entailments.

• Other Topics on Ontologies and Description Logics

  We also offer some further thesis topics on ontologies and description logics. These topics are particularly interesting for students with an interest in ontologies and/or logics.