BriefGPT.xyz
Jun, 2019
使用主题模板和结构化卷积解码器生成摘要
Generating Summaries with Topic Templates and Structured Convolutional Decoders
HTML
PDF
Laura Perez-Beltrachini, Yang Liu, Mirella Lapata
TL;DR
本论文提出一种结构化卷积解码器，通过内容结构引导，将多句文本生成分解为多个子任务，通过在不同领域的数据集上进行比较，证明该模型在内容覆盖方面取得了更好的表现，并通过自动和人工评估进行验证。
Abstract
Existing
neural generation
approaches create multi-sentence text as a single sequence. In this paper we propose a
structured convolutional decoder
that is guided by the content structure of
→