Open Liwink opened 7 years ago
???
Hello @Liwink ,
Thank you for your post. You might find more support for this kind of issue within one of our community boards. In particular, the Facebook group has a lot of members many of whom are ML experts and are keen on discussing applications of this library.
Specifically, there is a
Facebook group Stack Overflow tag Google group
If you do decide to move this to one of our other community boards, please consider closing this issue.
Thanks, Christian
Are there any new ideas to avoid overfitting with fasttext now? @Liwink @xharrietx411
It is amazing to use fastText to classify documents for its speed and accuracy. But I have no idea about how to avoid overfitting effectively. When I use bigrams and train more epochs, the training accuracy is greater, but the validation accuracy is lower.
How can I avoid overfitting effectively when using fastText to learn a text classifier? Thanks.