BriefGPT.xyz
Oct, 2022
自动新闻写作的计算架构比较
Comparing Computational Architectures for Automated Journalism
HTML
PDF
Yan V. Sym, João Gabriel M. Campos, Marcos M. José, Fabio G. Cozman
TL;DR
比较了常用的自然语言生成方法，探讨模板模型、管道模型和神经网络模型在从结构化数据生成葡萄牙语文本时的表现，并发现中间步骤较多的方法能比端到端的神经网络模型生成更好的文本。
Abstract
The majority of NLG systems have been designed following either a template-based or a
pipeline-based architecture
. Recent
neural models
for data-to-text generation have been proposed with an end-to-end deep learn
→