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
Login to add comment
Other posts in this group
Article URL: https://arxiv.org/abs/2506.02774
Comments URL: https://news.ycombinator.c
Article URL: https://thezvi.substack.com/p/o3-turns-pro
Comments URL: https:
Article URL: https://spectrum.ieee.org/jpeg-image-format-history
Article URL: https://substack.com/home/post/p-165655726
Comments URL: https:
