However it is interesting that LSTM can achieve good performance
with word vectors based on a small corpus even though it scored terrible in the semantic and syntactic analysis.
LSTM does perform better than the other classifiers, but it does require more data. If NLP tasks are to be solved in other domains that do not generate enough data for a LSTM to work properly it would be advisable to train a SVM using AvgWV. LSTM is more adaptable but knowing how to optimise the network does require domain knowledge and experience with gradient-decent classifiers.
Semi-Supervised Learning with Multi-View Embedding:
Rie Johnson
RJ Research Consulting
Tarrytown, NY, USA
Tong Zhang
Baidu Inc., Beijing, China
Rutgers University, Piscataway, NJ, USA