Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Learning to Compose Neural Networks for Question Answering #1

Open
ZihaoZheng98 opened this issue Sep 25, 2021 · 1 comment
Open

Learning to Compose Neural Networks for Question Answering #1

ZihaoZheng98 opened this issue Sep 25, 2021 · 1 comment

Comments

@ZihaoZheng98
Copy link
Owner

ZihaoZheng98 commented Sep 25, 2021

NAACL 16

one sentence: 根据特定问题,构建特定神经网络,提高了模型的组合泛化性以及可解释性。

为了提高模型对全新问题组合的理解能力,作者提出了Neural module network,简单来说是将问题分解为句法树,然后按照作者预定义的规则,将句法树转换为若干个布局,使用一个神经网络Z对不同布局打分得到不同布局的分布,最后采样得到最终的布局。将布局中特定节点替换为特定神经网络模块即得到最终的神经网络Y。在预测时,将图片输入到问题构建出的神经网络中,得到预测结果。

亮点:训练数据不包含对Z的标注数据,作者使用强化学习策略梯度的方式对Z网络进行参数更新。
论文推荐指数:较推荐,其中强化学习更新参数的部分,能够借鉴到很多中间有隐变量的模型中。是绕不开的坑。

@ZihaoZheng98
Copy link
Owner Author

image
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant