BriefGPT.xyz
Jun, 2019
用粒度逐渐调整的方法生成具有方面感知的长而详尽的评论
Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
HTML
PDF
Junyi Li, Wayne Xin Zhao, Ji-Rong Wen, Yang Song
TL;DR
本文提出了一种基于方面感知的精细到粗糙的文本生成模型，通过利用方面语义、句法轮廓和上下文信息来提高评论文本生成的自然度和连贯性，实验结果表明该方法有效。
Abstract
Generating long and informative review text is a challenging
natural language generation
task. Previous work focuses on word-level generation, neglecting the importance of topical and
syntactic characteristics
fr
→