I'm currently a PhD Student of Computer Science at the Deep Semantic Learning group at the University of Kassel. My interests lie in machine learning, data analysis, Information Retrieval and Natural Language Processing. Feel free to explore my repositories to see the projects I've been working on.

Here are some of the projects I've been involved in:

• Master Thesis: Leveraging LLM-Generated Hard Negatives for the Impostors Approach
  Repository: master-thesis
  Description: This repository contains the written work on my Master thesis, employing LLM-generated paraphrases as hard negatives for the Impostor approach of Koppel and Winter (2014).

• Bachelor Thesis: Identification of Key Information with Topic Analysis on Large Unstructured Text Data
  Repository: bachelor-thesis
  Description: This repository contains the written work on my Bachelor thesis, focusing on identifying key information using topic analysis techniques.

• Discord Detection in Time Series Data
  Repository: discord_detection
  Description: A project to identify discords in time series data using the HOT SAX methodology.

• Approaches for Finding Sample Pairs in Contrastive Learning
  Repository: master-seminar-ies
  Description: Work from my Master seminar focusing on methods to find sample pairs in contrastive learning, conducted under the Intelligent Embedded Systems chair.

• Text topic
  Repository: text_topic
  Description: This repository implements a pipeline to store various data of files from a large unstructured dataset. These fields are used for topic modeling (wordclouds, based on low-dimensional versions of embedding vectors, Named Entity Clustering and document-topic incidences). The information is aggregated and visualised using FCA. A comprehensive overview of the system can be found in the slides presented at the conference CONCEPTS'25 (September 08th-12th, 2025, Cluj-Napoca, Romania) or in the corresponding paper.

• Topic Analysis of Text Data
  Repository: topic-analysis-text-data
  Description: This repository provides methods and functions to find similar documents in terms of content and visual appearance, i.e. layout, from a large corpus of unstructured text data.

• Identifying fiscal fraud with anomaly detection techniques
  Repository: identifying-fiscal-fraud
  Description: Bachelor Seminar about exploring techniques to identify anomalies and fiscal fraud.

• Optimization of Spiking Neural Networks
  Repository: bachelor-seminar-kde
  Description: Bachelor Seminar about Spiking Neural Networks.

• 🔭 I’m currently working on Data Mining of large unstructured (text) data and Information Retrieval research projects.
• 🌱 I’m currently learning Argumentative search & Web search in the context of Information Retrieval.
• 👯 I’m looking to collaborate on Natural Language Processing, Information Retrieval projects and open-source initiatives.
• 💬 Ask me about Natural Language Processing, Information Retrieval and Data Mining.
• 😄 Pronouns: She/Her
• ⚡ Fun fact: I enjoy visualizing complex data through creative infographics!

• LinkedIn: Klara M. Gutekunst
• ORCID: https://orcid.org/0009-0002-6416-7873

Feel free to reach out if you're interested in collaborating or discussing any of my projects!