The author compares the performance of (Chat)GPT and BERT in detecting semantic changes over time, highlighting the strengths and weaknesses of each model.
(Chat)GPT performs worse than BERT in detecting short-term semantic changes but slightly lower in long-term changes.
(Chat)GPT performs worse than BERT in detecting short-term semantic changes but slightly lower in long-term changes.
(Chat)GPT performs worse than BERT in detecting short-term semantic changes but slightly worse in detecting long-term changes.