Amazon产品分类预测系统，对⽐多种机器学习和深度学习技术预测结果，使用BERT+CNN对比RNN、RCNN等多种方式提高模型性能
| 模型 | Test_Acc |
|---|---|
| BERT | 88.54% |
| BERT+CNN | 88.34% |
| BERT+RNN | 87.42% |
| BERT+RCNN | 88.01% |
| BERT+DPCNN | 88.40% |
| ERNIR | 94.09% |
| ERNIR+DPCNN | 94.20% |
-
Notifications
You must be signed in to change notification settings - Fork 1
libinhang/ShopSentiment-BERT
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
基于Bert+多种深度学习模型的购物网站评论关联与情感分析
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published