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.

• Combining KR with LLMs

  Projects focus on how to combine KR with Large language Models, including BERT models and generative LLMs like LLaMA and GPT series.

  • Ontology Text Alignment Using Large Language Models (BERT and Generative LLMS) ( Jieying, B.Sc./M.Sc. )

    Jieying Chen (j.chen2@vu.nl) This is a qualitative study where the goal is to look into common theories and disciplines that might influence novel Hybrid Intelligence methods. (continue reading)
    • Large Language Models
    • Ontology Engineering
    • Nature Langue Processing
    • BERT models
    • RAG

• Bias detection in LLMs

  These projects focus on how to detect bias in LLMs to ensure fairness in society.

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

    Jieying Chen (j.chen2@vu.nl) This is a qualitative study where the goal is to look into common theories and disciplines that might influence novel Hybrid Intelligence methods. (continue reading)
    • Fairness
    • Large Language Models
    • Social AI
    • BERT models

• 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.

• 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.

• Knowledge and Ontology Engineering

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

  • Identifying ancestor disciplines of Hybrid Intelligence ( Ilaria, B.Sc./M.Sc. )

    Ilaria Tiddi (i.tiddi@vu.nl) This is a qualitative study where the goal is to look into common theories and disciplines that might influence novel Hybrid Intelligence methods. (continue reading)
    • Hybrid Intelligence
    • Knowledge Engineering
    • Qualitative Surveys

  • Simulation of a micro-surgery knowledge-based robot. ( Ilaria, B.Sc./M.Sc. )

    Ilaria Tiddi (i.tiddi@vu.nl) Implementing a simulation of a micro-surgery knowledge-based robot. (continue reading)
    • Hybrid Intelligence
    • Knowledge Representation
    • Knowledge-based Robotics

  • Assessing Domain Coverage of an Ontology ( Romana, B.Sc./M.Sc. )

    Romana Pernisch (r.pernisch@vu.nl) In this project you will make use of an existing pipeline to investigate the coverage of a specific domain ontology against a corpus of text. (continue reading)
    • Domain Coverage
    • Ontology
    • Quality Assessment
    • Language Model
    • Reproducibility

  • Detecting the Need for Ontology Change ( Romana, B.Sc./M.Sc. )

    Romana Pernisch (r.pernisch@vu.nl) In this project you will develop a (potentially human-in-the-loop) pipeline to detect the need for change to an ontology based on domain documents (text). This can potentially by done using the existing coverage evaluation approach OntoEval with some additional steps. (continue reading)
    • Ontology/KG update
    • Domain Coverage
    • Ontology/KG
    • Human-in-the-Loop
    • Deep Learning/Language Model
    • Reproducibility

  • Framework/Proof of Concept for Automatic Ontology Updates ( Romana, B.Sc./M.Sc. )

    Romana Pernisch (r.pernisch@vu.nl) In this project you will develop a (human-in-the-loop) theoretical framework and engineer a proof of concept for automatic ontology updates. The updates are suggested using an agent (bot) and the human needs to make decisions on the update and adjust if necessary. (continue reading)
    • Ontology/KG update
    • Ontology/KG
    • Human-in-the-Loop
    • Interaction
    • Framework
    • Proof of Concept

• Argument Mining

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

  • Exploring attacking arguments in the Computer Science Knowledge Graph (CS-KG) ( Ilaria, B.Sc./M.Sc. )

    Ilaria Tiddi (i.tiddi@vu.nl) The goal of the project is to extract argumentation graphs from the Computer Science Knowledge Graph. (continue reading)
    • Hybrid Intelligence
    • Argument Mining
    • Knowledge Graphs

• Knowledge-based Robotics

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

  • Improving Gaze Detection for Robotics ( Ilaria, B.Sc./M.Sc. )

    Ilaria Tiddi (i.tiddi@vu.nl) Improving the robot's gaze detection abilities. (continue reading)
    • Knowledge Representation
    • Knowledge-based Robotics
    • Computer Vision

  • Building a common-sense object dataset for Robots ( Ilaria, B.Sc./M.Sc. )

    Ilaria Tiddi (i.tiddi@vu.nl) Building a common-sense Knowledge Graph for Robotics applications. (continue reading)
    • Knowledge Representation
    • Knowledge-based Robotics
    • Knowledge Graphs

  • Building a system to recognise item owners ( Ilaria, B.Sc./M.Sc. )

    Ilaria Tiddi (i.tiddi@vu.nl) This project will research methods for object identification and classification in robotics to distinguish ownership of objects. (continue reading)
    • Knowledge Representation
    • Knowledge-based Robotics
    • Computer Vision

• Knowledge Graph-based Question Answering

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

• Knowledge Graphs and Deep Learning

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

• Formal Logics, Modal Logics

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

• Ontologies and Reasoning

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

  • Enhancing Ontological Reasoning with SWRL Rules: A Semantic Approach ( Ameneh, B.Sc. )

    Ameneh Naghdi Pour (a.naghdipour@vu.nl, j.y.chen@vu.nl) This project focuses on how SWARL rules can support inferencing of new knowledge and improve decision-making situations. (continue reading)
    • Ontology
    • SWARL rule
    • Inference
    • Desicion-making

  • 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.

  • Discussion Games for Abstract Dialectical Frameworks ( Atefeh, M.Sc., B.Sc. )

    Atefeh Keshavarzi (a.keshavarzi.zafarghandi@vu.nl) The initial aim of this project is to implement an efficient two-player discussion game for abstract dialectical frameworks, recently developed for preferred semantics. (continue reading)
    • Computational argumentation
    • Discussion Games
    • Preferred Semantics
    • Implementation

• 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

  • Using LLMs and Argumentation Formalisms to Detect Drug-Drug Interactions for Multimorbid Patients ( Atefeh, M.Sc./B.Sc. )

    Atefeh Keshavarzi (a.keshavarzi.zafarghandi@vu.nl) This project aims to provide an AI system that recommends interaction-free drugs for multimorbidities using large language models (LLMs) and formal argumentation. (continue reading)
    • Computational argumentation
    • Prompting
    • LLMs

• 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.

  • Using Abstract Dialectical Frameworks for Inconsistency-Tolerant Query ( Atefeh, M.Sc. )

    Atefeh Keshavarzi (a.keshavarzi.zafarghandi@vu.nl) The initial aim of this project is to provide a solver for the newly introduced abstract dialectical framework (ADF) semantics and efficiently implement the recently introduced transformation from a dataset to an ADF. (continue reading)
    • Computational argumentation
    • nconsistency-Tolerant Reasoning
    • Semantics
    • Implementation

• 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.