Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Methias, Sameh"'
We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer. This is in contrast to previous approaches, that either used reinfor
Externí odkaz:
http://arxiv.org/abs/2211.10688
