[matachuan]

That's how NLP can be a dead end by putting your faith on NN.

[riku_iki]

So far this dead end outperforms traditional ways though.

[matachuan]

Lol for sure any NN-based approach can claim to outperform traditional ways while half of CVPR paper results cannot be reproduced.

[posterboy]

From reading papers on WaveNet and AlphaGo, the problem seems to be incomplete information in the papers, but I am not going to argue with the popular results.

[riku_iki]

> while half of CVPR paper results cannot be reproduced.

even if just another half of results are proven to outperform traditional approaches, is it strong enough trend?

[matachuan]

You clearly did not see that was sarcastic.

[amirouche]

CVPR?

[mindcrime]

Conference on Computer Vision and Pattern Recognition