I am starting a sentiment analysis project on a corpus of text. I would like to augment my work with a pre-trained fasttext vector (english wikipedia, https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md ).
I cannot seem to find any examples of using such a pre-trained vector with mxnet. Does anyone have some sample code they might be able to share? A link to a something that I wasn’t able to find for whatever reason?
Any general advice on doing word embeddings with mxnet would be great too…the documentation seems a bit thin overall in this area.