Definition modeling, the task of generating new definitions for words in context, holds great prospect as a means to assist the work of lexicographers in documenting a broader variety of lects and languages, yet much remains to be done in order to assess how we can leverage pre-existing models for as-of-yet unsupported languages. In this work, we focus on adapting existing models to Belarusian, for which we propose a novel dataset of 43,150 definitions. Our experiments demonstrate that adapting a definition modeling systems requires minimal amounts of data, but that there currently are gaps in what automatic metrics do capture.
@article{arxiv.2507.09536,
title = {Adapting Definition Modeling for New Languages: A Case Study on Belarusian},
author = {Daniela Kazakouskaya and Timothee Mickus and Janine Siewert},
journal= {arXiv preprint arXiv:2507.09536},
year = {2025}
}