Improving Linguistic Data with LLMs
We have developed a novel methodology for extracting knowledge graphs from digital linguistic databases that is tailored to morphologically complex languages.
About saras
This author has yet to write their bio.Meanwhile lets just say that we are proud saras contributed a whooping 13 entries.
Entries by saras
Advanced grammatical analysis of multilingual corpora
12. 6. 2025 in Blog Posts /by sarasAs part of the LLM4DH project, we will develop a novel approach to grammatical analysis of multilingual corpora by augmenting state-of-the-art LLMs with the Universal Dependencies (UD) data.
Workshop: AI Methods for Research of Folkloristic Narratives
6. 6. 2025 in Blog Posts, Novice /by sarasOn June 13, 2025, we are organising a workshop at UL FRI. The topic of the workshop is AI Methods for Research of Folkloristic Narratives.
CLASSLA-Express Workshops in 2025
14. 5. 2025 in Blog Posts /by sarasCLASSLA-Express workshops aim to show participants how to use the CLASSLA web corpora in language research. The workshops comprise hands-on exercises showing how to create queries in corpora for Bulgarian, Croatian, Macedonian, Serbian and Slovene.
Behind the scenes of developing spell and grammar correction LLM for Slovenian: combining authentic and synthetic data
28. 4. 2025 in Blog Posts, Novice /by sarasThis article briefly explains the methods and prompts used to develop spelling and grammar correction LLMs for the Slovenian language.
CONTACT
Content:
marko.robniksikonja@fri.uni-lj.si
DURATION
Duration of the project:
September 2024 – September 2027
LOCATION
Faculty of Computer and Information Science
Večna pot 113, SI-1000 Ljubljana, Slovenia
Room: R2.06 (2nd floor)
FINANCED BY
