Skip to main content
. Author manuscript; available in PMC: 2016 Apr 14.
Published in final edited form as: Adv Neural Inf Process Syst. 2015 Dec;28:919–927.

Table 4.

IMDB: previous error rates (%).

NB-LM 1-3grams [18] 8.13 –
[11]'s best CNN 7.67 –
Paragraph vectors [14] 7.46 Unlab.data
Ensemble of 3 models [18] 7.43 Ens.+unlab.
Our best 6.51 Unlab.data