Skip to content

WikiQA,复现论文《APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND AN OPEN TASK》

License

Notifications You must be signed in to change notification settings

WenRichard/CNN-in-Answer-selection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WikiQA on QACNN

复现论文《APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND AN OPEN TASK》

本项目采取了论文中最好的模型进行实验,数据集采用WikiQA,后期会上传insuranceQA的实验结果
模型图如下:
model
实验结果

Model CNN share Dropout Parameters Margin Epoch MAP MRR
QACNN No 0.5 2115200 0.5 100 0.655 0.673
QACNN Yes 0.5 481664 0.5 100 0.684 0.697
QACNN Yes 0.5 481664 0.25 100 0.668 0.674
QACNN Yes 0.5 481664 0.2 100 0.690 0.695

LossPairwise Loss

有时间就会更新QA实验,有兴趣的同学可以follow一下,也欢迎Fork和Star!
留言请在Issues或者email [email protected]

About

WikiQA,复现论文《APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND AN OPEN TASK》

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages