BriefGPT.xyz
Apr, 2016
使用卷积神经网络对问答对中的关系信息进行建模
Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks
HTML
PDF
Aliaksei Severyn, Alessandro Moschitti
TL;DR
本文提出了卷积神经网络来学习问题和回答句子的最佳表现形式，并使用成对匹配的关系信息进行编码，这使得神经网络可以更好地捕捉到问题和答案之间的交互作用，从而有效地提高了准确性。
Abstract
In this paper, we propose
convolutional neural networks
for learning an optimal representation of
question and answer sentences
. Their main aspect is the use of
→