I've taken a class from Allen and used his books. In the context of his classes they are very good and the short readings can be useful, but taken as a reference like many other textbooks are they don't do as much.
The Business Insider article links this[0] one as the original article in the footnote. It's very similar and also worth a read (and I think it shouldn't require running code to be read)
This is an awesome explanation of those papers! Does anyone have any cool examples of word2vec being used in a project? I'd be interested in seeing what people could make with it.
Document type classification. We wanted to predict which of these k classes a new text document was.
We trained 100-dim word vectors on all the text content we currently have, plus some 30,000 wiki articles related to the business. New content comes in, convert words to vecs, average them, and use that resulting vec as the input to a basic classifier.
For how simple that is, the method is unreasonably good. Widely applicable too.
For a lot of people (myself included) it's not intuitive to pay attention to these things. Do you have any good references for similar design patterns?
I'd love an early access code! I filled out the typeform on the usejournal site as well! My email is <hnname>@gardeneast.com