Why aren’t you using pretrained models?

To show how sim­ply this can be done, let's build a seman­tic search func­tion that could be of use for any­one tasked with writ­ing text. To find bet­ter words and expres­sions, you need to think of a word, look it up, and then chase ref­er­ences to explore the pos­si­bil­i­ties. What if, in addi­tion to this for­ward search, a com­puter could look in the other direc­tion? Then you may want to look at the code, even if you are not a pro­gram­mer: we need about 16 lines of Python to load the data, run it through a neural net­work, index it and start search­ing. With the Web­ster-Vec­tors in mem­ory, we can now query this dataset by encod­ing a search phrase into a query vec­tor. To search for words, we com­pare how close the query is to vec­tors in the dataset. All that's left to do for us is to return the words asso­ci­ated with these neigh­bor vec­tors.