carpedm20/variational-text-tensorflow

Bad performance in document classification

Open

#2 aberto em 12 de jan. de 2017

Ver no GitHub
 (1 comment) (0 reactions) (0 assignees)Python (76 forks)github user discovery
enhancementhelp wanted

Métricas do repositório

Stars
 (535 stars)
Métricas de merge de PR
 (Métricas PR pendentes)

Description

Hi Taehoon,

Thank you for sharing your implementation. Have you tried applying the NVDM model in some downstream tasks like document classification? I did not find such experiments in the original paper, so I did my own. After running your code on the 20 Newsgroups data set and training a simple classifier on learned document representations, I got a quite low accuracy (5% in my experiment). In addition, I found when I set max_iter too large, I got NaN errors when running the code.

Any help will be highly appreciated!

Thanks, Hugo

Guia do colaborador