Opinion Mining with Deep Recurrent Neural Networks(cs.cornell.edu)
cs.cornell.edu
Opinion Mining with Deep Recurrent Neural Networks
http://www.cs.cornell.edu/~oirsoy/drnt.htm
2 comments
Could someone explain the results of this, rather than the code and the theory?
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.
tldr: Deep RNN's are better than shallow RNN's and CRF's for several NLP tasks.
OT: Am I the only one practically unable to read the abstract? Grey on white does not work well for my eyes.