Re:Opinion Mining with Deep Recurrent Neural Networks
by woah on Monday July 06, 2015 @04:28PM
(#9841962)
Could someone explain the results of this, rather than the code and the theory?
[ Parent
| on HN ]
Re:Opinion Mining with Deep Recurrent Neural Networks
by newsposter123 on Monday July 06, 2015 @04:53PM
(#9842111)
This is from the "Conclusions" slide:
• Deep recurrent nets perform better than their shallow
counterparts of the same size on both DSE and ESE
extraction.
• Both shallow and deep RNNs capture aspects of
subjectivity, but deep RNNs seem to better handle the
expression boundaries.
• Deep RNNs outperforms previous baselines CRF and
semi-CRF without having access to the dependency or
constituency trees, opinion lexicons or POS tags, even
when (semi)CRF has access to word vectors.
tldr: Deep RNN's are better than shallow RNN's and CRF's for several NLP tasks.