JianLiu91
JianLiu91
I think this is a kind of raw since it counts event kind of tag (including I-XXXX) into the computation. Using the standard evaluation tool is more preferable, such as...
It is the KL divergence of two Gaussian distribution (i.e., the prior p(z) ~ N(0, 1) and the posterior q(z|h) ~ N(mu, var). See the original paper https://arxiv.org/pdf/1312.6114.pdf
Besides, can you model successfully recovery an original sentence in the training set, by using the mean value?
When I run the code, it says that IOError: [Errno 2] No such file or directory: 'data/yelp/vocab.0.970.pk' Where can I find/generate this file?