BriefGPT.xyz
Feb, 2016
通过结合卷积和循环层实现高效的字符级文档分类
Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers
HTML
PDF
Yijun Xiao, Kyunghyun Cho
TL;DR
本研究提出了一种利用卷积和循环层来高效编码字符输入的神经网络架构，用于文档分类任务，与仅具有卷积层的字符级模型相比，具有相当的性能而参数更少。
Abstract
document classification
tasks were primarily tackled at word level. Recent research that works with
character-level inputs
shows several benefits over word-level approaches such as natural incorporation of morphe
→