Dominic P. Fischer

Computational linguist with a BA and an MSc in Computational Linguistics and Language Technology from the University of Zurich (MSc GPA 5.7/6), with a minor in Comparative Romance Linguistics.

Research assistant at the Department of Computational Linguistics, UZH (2023–2026), in the projects Bullinger Digital and Machine Translation for Romansh Idioms. Evaluated LLM-based translation of historical texts and developed a dictionary-based lemmatizer for Romansh, released as a Python package. Six published papers across the two projects.

Further academic activities: tutor for introductory computational linguistics courses and Database Systems (2022–2024), and president of the UZH Computational Linguistics student association (2024–2026).

Masters thesis: training byte-level language models, modeled on Meta AIs Byte Latent Transformer (BLT), and evaluating their fairness across languages.

Technical experience: Python, PyTorch, and Hugging Face; LLMs (APIs, evaluation, RAG, MCP); model training and evaluation; REST APIs and full-stack development (Flask, React, Streamlit); and AI-assisted development.

Languages: fluent in German, English, French, and Romanian, with strong proficiency in Italian, Spanish, and Portuguese.

selected publications

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.
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.