Elisabeth L. Fittschen

Hello, my name is Elisabeth and I will be applying to CS (NLP) PhD positions in the 2025 cycle.

I am a Master’s student at the University of Hamburg ⚓, and am currently a visiting student at the Johns Hopkins Centre for Language and Speech Processing (CLSP) under the supervision of Dr. Tom Lippincott. Prior to this, I completed a Bachelor’s of Computer Science at the Technical University of Clausthal, where my thesis focused on real time computer graphics optimization (transparency rendering in raytracing).

My research interests lie in the efficiency of modern language models and questions surrounding how to best extend their recursive reasoning abilities.

news

May 16, 2024	We received Honorable Mentions at the Student Game Competition CHI 2024! Check out the details here.
May 11, 2024	Excited to announce that our paper “Language of Zelda: Facilitating Language Learning Practices Using ChatGPT” is published at the “Student Games Competition” at CHI 2024
Mar 17, 2024	First paper “AnnoPlot: Interactive Visualizations of Text Annotations” has been accepted for publication as a System Demonstration at the EACL 2024!

selected publications

AnnoPlot: Interactive Visualizations of Text Annotations

Elisabeth Fittschen, Tim Fischer, Daniel Brühl, and 3 more authors

In Conference of the European Chapter of the Association for Computational Linguistics, 2024

Abs

This paper presents AnnoPlot, a web application designed to analyze, manage, and visualize annotated text data.Users can configure projects, upload datasets, and explore their data through interactive visualization of span annotations with scatter plots, clusters, and statistics. AnnoPlot supports various transformer models to compute high-dimensional embeddings of text annotations and utilizes dimensionality reduction algorithms to offer users a novel 2D view of their datasets.A dynamic approach to dimensionality reduction allows users to adjust visualizations in real-time, facilitating category reorganization and error identification. The proposed application is open-source, promoting transparency and user control.Especially suited for the Digital Humanities, AnnoPlot offers a novel solution to address challenges in dynamic annotation datasets, empowering users to enhance data integrity and adapt to evolving categorizations.
Language of Zelda: Facilitating Language Learning Practices Using ChatGPT

Sukran Karaosmanoglu, Elisabeth Fittschen, Hande Eyicalis, and 4 more authors

In Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA, 2024

Abs DOI

The Language of Zelda is an educational game that re-imagines “The Legend of Zelda: A Link to the Past” for French language learning. With the integration of ChatGPT for non-player characters (NPCs), the game allows players to interact with NPCs to practice French through gameplay, puzzles, and quests. Our approach bridges the gap between declarative and procedural language knowledge, offering an engaging, immersive learning experience. The game’s adaptive dialogues cater to various proficiency levels, enhancing both education and entertainment values. Our work illustrates the potential of combining AI with game-based learning to create effective, enjoyable language education tools.