Experimenting with terminology extraction tools: suggestions for an exercise with translation students

Abstract

This article reports on a terminology extraction project conducted with second-year master’s students enrolled in a specialized translation program. Students engaged in terminological extraction tasks based on a specialized linguistic corpus, with four different tools: a computer-assisted translation (CAT) software, a concordancer, an online terminology extraction platform, and a large language model (LLM). Students were subsequently required to perform a comparative analysis of the outputs generated by each tool, with the ultimate objective of compiling a monolingual glossary. The article offers a reflective evaluation of the project, which aimed to develop students’ evaluative judgment on the results generated by the tools – a human competence increasingly essential in the evolving landscape of language technologies.