Generating Wikipedia by Summarizing Long Sequences
Peter J. Liu, Saleh, Mohammad, Etienne Pot et al. · arXiv (Cornell University) · 2018
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.
Cited by 60 works. doi:10.48550/arxiv.1801.10198 Open-access PDF
Authors
References
- Attention Is All You Need
- The PageRank Citation Ranking : Bringing Order to the Web
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- A Neural Attention Model for Abstractive Sentence Summarization
- TextRank: Bringing Order into Text
- DBpedia – A large-scale, multilingual knowledge base extracted from Wikipedia
- A Deep Reinforced Model for Abstractive Summarization
- SQuAD: 100,000+ Questions for Machine Comprehension of Text
- Abstractive Sentence Summarization with Attentive Recurrent Neural Networks
- Overview of DUC 2005