Can AI Understand Croatian Idioms? Assessing Large Language Models in Lexicographic Tasks
Bibliographic Data
| ID | 20467290 |
|---|---|
| Authors | Ivana Filipović Petrović (0000-0001-8952-0202, Croatian Academy of Sciences and Arts), Slobodan Beliga (0000-0003-1407-6156, University of Rijeka) |
| Year | 2025 |
| Volume | 65 |
| Issue | 3 |
| Publication date | 2025-12-22 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Contributions to Contemporary History (JOURNAL) |
| Journal identifiers | ISSN: 0353-0329 • E-ISSN: 2463-7807 |
| Publisher | Institut za novejso zgodovino (PUBLISHER) |
| DOI | 10.51663/pnz.65.3.09 |
| OpenAlex | W7116937855 |
| Language | EN |
| References cited | 10 |
This paper explores the potential of ChatGPT in automating two lexicographic tasks within the Online Dictionary of Croatian Idioms (ODCI): (1) identifying semantic equivalents among idioms and (2) generating semantic fields for idiomatic expressions. The study evaluates how effectively AI can automate the process of distinguishing and grouping idioms by meaning, with the aim of reducing manual lexicographic work. As contemporary methodologies for employing language technologies continue to develop alongside technological progress, this research enhances understanding of AI capabilities in linguistic analysis. The findings suggest that ChatGPT shows considerable potential for conceptual organisation in lexicography. Nevertheless, challenges persist, especially regarding the unpredictable nature of AI-generated responses and the necessity for human post-editing
Computational linguistics · Croatian · Language Understanding · Lexicographical order · Linguistics, Language Diversity, and Identity · Natural Language Processing Techniques · Text Readability and Simplification
| Citation velocity | historical |
|---|---|
| Highly cited | No |