AI in Lexicography for Low-Resource Languages: The Case of the Georgian Language

The emergence of AI has accelerated the integration of chatbots into various fields, reducing the need for human involvement in many areas. Lexicography has been no exception, and since 2022 numerous studies have explored the role of AI in dictionary compilation. However, the role of AI in lexicography for low-resource languages such as Georgian has remained largely outside this discussion, as most existing research focuses on English – a high-resource lingua franca that may be regarded as the “mother tongue” of chatbots. Consequently, the performance of chatbots in low-resource languages remains underexplored, particularly with regard to whether AI can outperform human lexicographers on a broader scale.

The aim of this research is to examine the performance of ChatGPT in the context of a low-resource language such as Georgian and to analyse its lexicographic capabilities. This qualitative study investigates the extent to which ChatGPT can generate dictionary entries for a Georgian explanatory dictionary, including headwords, definitions, illustrative examples, grammatical information, usage labels, and etymological data.