In my NLP task, I use Glove to get each word embedding in a sentence, I getGlove gives 50 float numbers as an embedding for every word in my sentence, howmy corpus is large, and the resulted model is also large to fit my machine, I'm looking for a way to reduce this numbereach word embedding from 50 numbers to something less, maybe one floating number is possible, is there an approach to do that?
Could anyI was thinking about an aggregation method work? Likeapproach,like taking the average. of the 50 numbers, would that work?