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.
I would be interested to know more as to how people think in the language of mathematics when deriving and reading mathematical formulas as I really struggle with it if I don't get the intuition.
"It is not unthinkable that if I would submit a love letter, it would be published sooner than an intelligent scholarly article by a young researcher."
tldr: Deep RNN's are better than shallow RNN's and CRF's for several NLP tasks.