We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents. We use extractive summarization to coarsely identify salient information and a neural abstractive model to generate the article. For the abstractive model, we introduce a decoder-only architecture that can scalably attend to very long sequences, much longer than typical encoder- decoder architectures used in sequence transduction. We show that this model can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. When given reference documents, we show it can extract relevant factual information as reflected in perplexity, ROUGE scores and human evaluations.
@article{arxiv.1801.10198,
title = {Generating Wikipedia by Summarizing Long Sequences},
author = {Peter J. Liu and Mohammad Saleh and Etienne Pot and Ben Goodrich and Ryan Sepassi and Lukasz Kaiser and Noam Shazeer},
journal= {arXiv preprint arXiv:1801.10198},
year = {2018}
}