Expository documents are vital resources for conveying complex information to readers. Despite their usefulness, writing expository text by hand is a challenging process that requires careful content planning, obtaining facts from multiple sources, and the ability to clearly synthesize these facts. To ease these burdens, we propose the task of expository text generation, which seeks to automatically generate an accurate and stylistically consistent expository text for a topic by intelligently searching a knowledge source. We solve our task by developing IRP, a framework that overcomes the limitations of retrieval-augmented models and iteratively performs content planning, fact retrieval, and rephrasing. Through experiments on three diverse, newly-collected datasets, we show that IRP produces factual and organized expository texts that accurately inform readers.
@article{arxiv.2305.03276,
title = {Expository Text Generation: Imitate, Retrieve, Paraphrase},
author = {Nishant Balepur and Jie Huang and Kevin Chen-Chuan Chang},
journal= {arXiv preprint arXiv:2305.03276},
year = {2023}
}