24 datasets found

A conditional language generation model with Big Five Personality (BFP) feature vectors as input context, which writes human-like short texts.

The MS MARCO NLGen dataset is a collection of natural language generation tasks, where the goal is to generate natural-sounding answers to questions.

Automatic evaluations for natural language generation (NLG) conventionally rely on token-level or embedding-level comparisons with the text references. This is different from...

The authors propose a novel approach that incorporates parameter-efficient tuning to better optimize control tokens, thus benefitting controllable generation.