Appropriate Microplanning Choices for Low-Skilled Readers

Sandra Williams, Ehud Reiter

Abstract: We have developed a set of microplanning choice rules which are intended to enable Natural Language Generation (NLG) systems to generate appropriate texts for readers with below-average literacy, focusing in particular on choices related to how discourse structure is expressed (cue phrases, ordering, sentence structure). Evaluation experiments suggest that our rules do enhance the readability of texts for low-skilled readers, although there is still room for improvement.