I've been playing with embeddings and wanted to try out what results the embedding layer will produce based on just word-by-word input and addition / subtraction, beyond what many videos / papers mention (like the obvious king-man+woman=queen). So I built something that doesn't just give the first answer, but ranks the matches based on distance / cosine symmetry. I polished it a bit so that others can try it out, too.
For now, I only have nouns (and some proper nouns) in the dataset, and pick the most common interpretation among the homographs. Also, it's case sensitive.
Comments URL: https://news.ycombinator.com/item?id=43988533
Points: 31
# Comments: 34
Zaloguj się, aby dodać komentarz
Inne posty w tej grupie
Longtime user posting from a new account out of an abundance of caution.
I founded an e-commerce marketplace startup. We use PayPal's Multiparty APIs (PayPal Commerce Platform) for checkout. For
Article URL: https://jimmyhmiller.com/machine-code-isnt-scary


Article URL: https://wordle.chengeric.com/
Comments URL: https://news.ycombinator.com/ite