How to avoid overfitting when doing text classification?

[Liwink]

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.

[xharrietx411]

???

[cpuhrsch]

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

[AbhiPawar5]

Are there any new ideas to avoid overfitting with fasttext now? @Liwink @xharrietx411