Automatically generating WordNet with LLMs
Organization
TartuNLP
Abstract
The aim is to test the ability of LLMs like GPT4 and Llama2 to generate lexical-semantic databases like WordNet. This sort of generation can be done for multiple languages and can start from zero or be used to expand an existing WordNet. The final goal is to test, how much of the generated material overlaps with manually created data for evaluation purposes.
Graduation Theses defence year
2023-2024
Supervisor
Mark Fishel
Spoken language (s)
Estonian, English
Requirements for candidates
Python, basic NLP
Level
Bachelor, Masters
Application of contact
Name
Mark Fishel
Phone
E-mail