Generating Wikipedia by Summarizing Long Sequences
Authors | Peter J. Liu Mohammad Ahmad Saleh Etienne Pot Ben Goodrich Ryan Sepassi Lukasz Kaiser Noam Shazeer |
---|---|
Publication date | 2018 |
Links | Original Preprint |
Generating Wikipedia by Summarizing Long Sequences - scientific work related to Wikipedia quality published in 2018, written by Peter J. Liu, Mohammad Ahmad Saleh, Etienne Pot, Ben Goodrich, Ryan Sepassi, Lukasz Kaiser and Noam Shazeer.
Overview
Authors show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents. Authors use extractive summarization to coarsely identify salient information and a neural abstractive model to generate the article. For the abstractive model, authors introduce a decoder-only architecture that can scalably attend to very long sequences, much longer than typical encoder- decoder architectures used in sequence transduction. Authors show that this model can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. When given reference documents, authors show it can extract relevant factual information as reflected in perplexity, ROUGE scores and human evaluations.
Embed
Wikipedia Quality
Liu, Peter J.; Saleh, Mohammad Ahmad; Pot, Etienne; Goodrich, Ben; Sepassi, Ryan; Kaiser, Lukasz; Shazeer, Noam. (2018). "[[Generating Wikipedia by Summarizing Long Sequences]]".
English Wikipedia
{{cite journal |last1=Liu |first1=Peter J. |last2=Saleh |first2=Mohammad Ahmad |last3=Pot |first3=Etienne |last4=Goodrich |first4=Ben |last5=Sepassi |first5=Ryan |last6=Kaiser |first6=Lukasz |last7=Shazeer |first7=Noam |title=Generating Wikipedia by Summarizing Long Sequences |date=2018 |url=https://wikipediaquality.com/wiki/Generating_Wikipedia_by_Summarizing_Long_Sequences}}
HTML
Liu, Peter J.; Saleh, Mohammad Ahmad; Pot, Etienne; Goodrich, Ben; Sepassi, Ryan; Kaiser, Lukasz; Shazeer, Noam. (2018). "<a href="https://wikipediaquality.com/wiki/Generating_Wikipedia_by_Summarizing_Long_Sequences">Generating Wikipedia by Summarizing Long Sequences</a>".