Use GloVe instead of the default spacy embeddings

[AndreiBarsan]

We're currently using 300-d Goldberg and Levy 2014 embeddings, the default from the spacy library the original blogpost was using (https://avisingh599.github.io/deeplearning/visual-qa/).

The author of that post mentioned that using GloVe embeddings should significantly improve accuracy.

[moisestg]

For the CIL project I used word2vec embeddings trained on the text itself (in this case the questions themselves) and worked quite well

[AndreiBarsan]

Awesome! I think we could try both, I guess. Gensim FTW! I'm only a bit worried that training locally may not be too helpful because many questions don't really offer that much co-occurrence information between words (as opposed to training on a Wikipedia dump, for instance).

[bernhard2202]

You can also try to make the embeddings not fixed like now but add a lookup layer which retrains word embeddings. But this blows up parameters and training time, but I guess it is worth a shot. See also: https://github.com/fchollet/keras/issues/853

[AndreiBarsan]

@bernhard2202 It may still help if we also train the embeddings. But perhaps we could leave it as low-priority.

[AndreiBarsan]

Oh, and regarding GloVe, their changelog mentions that "To reduce memory usage and loading time, we've trimmed the vocabulary down to 1m entries.", which means we may be able to squeeze a little bit more accuracy by using the untrimmed (1.9M entry OR even the 2.2M entry one) vocabulary from http://nlp.stanford.edu/projects/glove/. This should probably be low-priority anyway.

And yes, it seems that when the blogpost was originally written, spacy was not using GloVe, but they switched to using GloVe vectors in the meantime.