Liu, P.J.; Saleh, M.; Pot, E.; Goodrich, B.; Sepassi, R.; Kaiser, L.; Shazeer, N.: Generating Wikipedia by summarizing long sequences (2018)
0.00
0.004354783 = product of:
0.060966957 = sum of:
0.060966957 = weight(_text_:source in 773) [ClassicSimilarity], result of:
0.060966957 = score(doc=773,freq=2.0), product of:
0.15900996 = queryWeight, product of:
4.9575505 = idf(docFreq=844, maxDocs=44218)
0.0320743 = queryNorm
0.38341597 = fieldWeight in 773, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.9575505 = idf(docFreq=844, maxDocs=44218)
0.0546875 = fieldNorm(doc=773)
0.071428575 = coord(1/14)
- 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.