In-Context Learning for Upper Sorbian to German Translation: Comparing Lexical and Morpho-Syntactic Information
MCML Authors
Marion Di Marco
Dr.
Alexander Fraser
Prof. Dr.
Core PI
Abstract
Marion Di Marco
Dr.
Alexander Fraser
Prof. Dr.
Core PI
Abstract
LLM-based translation remains challenging for low-resource languages, as LLMs often lack linguistic knowledge due to their limited representation in pre-training data. This is particularly problematic for morphologically rich languages where a large vocabulary can lead to further data sparsity. Previous work has shown that providing external guidance on the source sentence in the form of language-specific information can help LLMs with tasks such as machine translation. In this study, we investigate zero-shot context augmentation for Upper Sorbian-to-German translation by enriching prompts with different types of contextual information: translation candidates in the form of bilingual dictionary entries, and morpho-syntactic analysis provided through morphological tagging. We first compare the effectiveness of these types of information in a zero-shot setting and then evaluate whether they generalize across additional experimental settings. We find that context-augmented prompting can improve Upper Sorbian-to-German translation. Contexts only containing translation candidates perform overall best, whereas morpho-syntactic analysis offers limited benefits, both on its own and in combination with lexical cues.
inproceedings SDF26
WMT 2026
11th Conference on Machine Translation. Budapest, Hungary, Oct 28-29, 2026. To be published. Preprint available.Authors
Q. Sheng • M. Di Marco • A. FraserLinks
URLResearch Area
BibTeXKey: SDF26