BriefGPT.xyz
Oct, 2018
一般适用规则不一定适合所有情况：生成和评估关键词的可变数量
Generating Diverse Numbers of Diverse Keyphrases
HTML
PDF
Xingdi Yuan, Tong Wang, Rui Meng, Khushboo Thaker, Daqing He...
TL;DR
本研究从建模和评估的角度解决了许多现有神经关键词生成模型中缺乏多样性问题，并提出了两种评估指标和一种新数据集 StackEx，从而能够控制输出数量并在所有数据集上优于强基线。
Abstract
Existing
keyphrase generation
studies suffer from the problems of generating duplicate phrases and deficient evaluation based on a fixed number of predicted phrases. We propose a
recurrent generative model
that g
→