Dominic P. Fischer

What inspired me to study Computational Linguistics? Not only wanting to study language(s), but to actually create and innovate using language! The rapid recent advancements in NLP and AI, coinciding with the begin of my studies, have made just that possible.

Professionally, a special interest of mine are LLMs with their vast capabilities, useful in many different fields, with many avenues still unexplored, and even more coming up due to the continuous—yearly, monthly, even weekly—breakthroughs.

This requires constant adaptation, a never-ending willingness to learn, to grow. This aligns well with my personal values, which is well-illustrated by my passion for languages: I never shy away from challenging myself, because I am convinced that good things require effort—and good people. Language helps foster connection, which is at the heart of my passion for languages.

I truly believe that techology is there to help make peoples’ lives easier, that we ought to embrace it and always strive to find better solutions to existing problems. However, the true drivers of technology are the people behind it, and we must never forget that.

Which brings me back to Computational Linguistics: it sits at the intersection of technology and human communication through language—and that is exactly where I want to be.

news

Jun 21, 2025	I have just set up my Github portfolio!

selected publications

LLM-based Machine Translation and Summarization for Latin

Martin Volk, Dominic P Fischer, Lukas Fischer, and 4 more authors

In Proceedings of the Third Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) at LREC/COLING 2024, May 2024

Abs DOI PDF

This paper presents an evaluation of machine translation for Latin. We tested multilingual Large Language Models, in particular GPT-4, on letters from the 16th century that are in Latin and Early New High German. Our experiments include translation and cross-language summarization for the two historical languages into modern English and German. We show that LLM-based translation for Latin is clearly superior to previous approaches. We also show that LLM-based paraphrasing of Latin paragraphs from the historical letters produces English and German summaries that are close to human summaries published in the edition.
LLM-based Translation Across 500 Years. The Case for Early New High German

Martin Volk, Dominic P Fischer, Patricia Scheurer, and 2 more authors

In Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024), Sep 2024

Abs DOI PDF Poster

The recently developed large language models (LLMs) show surprising translation capabilities for modern languages. In contrast, this paper investigates the ability of GPT-4 and Gemini to translate 500-year-old letters from Early New High German into modern German. We experiment with a corpus from the 16th century that is partly in Latin and partly in ENH-German. This corpus consists of more than 3000 letters that have been edited and annotated by experts from the Institute of Swiss Reformation Studies. We exploit their annotations for the evaluation of machine translation from ENH-German to German. Our experiments show that using the lexical footnotes by the editors in the prompts or directly injected into the text leads to high quality translations.