Header

UZH-Logo

Maintenance Infos

LLM-based Machine Translation and Summarization for Latin


Volk, Martin; Fischer, Dominic P; Fischer, Lukas; Scheurer, Patricia; Ströbel, Phillip (2024). LLM-based Machine Translation and Summarization for Latin. In: Third Workshop on Language Technologies for Historical and Ancient Languages -- LT4HALA (at LREC/COLING), Torino, 25 May 2024.

Abstract

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.

Abstract

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.

Statistics

Downloads

80 downloads since deposited on 02 May 2024
80 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Uncontrolled Keywords:Large Language Models, Machine Translation, Latin, Early New High German, GPT
Language:English
Event End Date:25 May 2024
Deposited On:02 May 2024 08:39
Last Modified:30 May 2024 11:38
OA Status:Green
  • Content: Accepted Version
  • Language: English