Keywords: abstractive summarization, Transformer, long sequences, natural language processing, sequence transduction, Wikipedia, extractive summarization
TL;DR: We generate Wikipedia articles abstractively conditioned on source document text.
Abstract: 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.
Code: [![github](/images/github_icon.svg) tensorflow/tensor2tensor](https://github.com/tensorflow/tensor2tensor) + [![Papers with Code](/images/pwc_icon.svg) 3 community implementations](https://paperswithcode.com/paper/?openreview=Hyg0vbWC-)
Data: [WikiSum](https://paperswithcode.com/dataset/wikisum), [Wikipedia Generation](https://paperswithcode.com/dataset/wikipedia-generation)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:1801.10198/code)