Disentangling Representations in Pre-Trained Language Models

Aniruddha Mahesh Dave
Pre-trained language models dominate modern natural language processing. They rely on self-supervision to learn general-purpose representations. Given the redundant information encoded in these representations, it is unclear what information encoded leads to superior performance on various tasks and whether it can be even better if it is encoded in an interpretable way. In this work, with stylistic datasets, we explore whether style and content can be disentangled from sentence representations learned by pre-trained language models....
This data repository is not currently reporting usage information. For information on how your repository can submit usage information, please see our documentation.