BriefGPT.xyz
Oct, 2017
基于分组稀疏卷积神经网络的带答案集合问题分类
Group Sparse CNNs for Question Classification with Answer Sets
HTML
PDF
Mingbo Ma, Liang Huang, Bing Xiang, Bowen Zhou
TL;DR
本研究通过引入新颖的组稀疏自编码器和组稀疏卷积神经网络，将答案信息考虑到问题建模中，从而在四个数据集上显著优于强基线模型。
Abstract
question classification
is an important task with wide applications. However, traditional techniques treat questions as general sentences, ignoring the corresponding
answer data
. In order to consider answer infor
→