News for hackers. Stuff that matters.
Re:What Kagglers Are Using for Text Classification by physicsyogi on Thursday December 27, 2018 @01:55PM (#18771566)
I’ve found that some CNNs consistently beat fasttext in terms of model quality. But I’ve beaten those CNNs and fasttext by doing transfer learning with ULMFit and fasts I. But if we’re talking training speed, fasttext is indeed aptly named.

There are no comments on this comment yet.