carpedm20/variational-text-tensorflow

Bad performance in document classification

Open

#2 geöffnet am 12. Jan. 2017

Auf GitHub ansehen
 (1 Kommentar) (0 Reaktionen) (0 zugewiesene Personen)Python (76 Forks)github user discovery
enhancementhelp wanted

Repository-Metriken

Stars
 (535 Stars)
PR-Merge-Metriken
 (PR-Metriken ausstehend)

Beschreibung

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

Contributor Guide