← Search

Alice Martin

1 accepted papers

2022

Learning Natural Language Generation with Truncated Reinforcement Learning

NAACL 2022long

This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original approach to train conditional languagemodels without a supervised learning phase, by only using reinforcement learning (RL). As RL methods unsuccessfully scale to large action spaces, we dynamically truncate th…