Expository Text Generation: Imitate, Retrieve, Paraphrase
This addresses the challenge of manually writing expository documents, which is time-consuming and requires synthesizing information from multiple sources, by automating the process for content creators and educators.
The paper tackles the problem of automatically generating expository text for a topic by proposing the IRP framework, which iteratively performs content planning, fact retrieval, and rephrasing, and shows through experiments on three new datasets that it produces factual and organized texts.
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.