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
Chcete-li přidat komentář, přihlaste se
Ostatní příspěvky v této skupině
Article URL: https://juhrjuhr.itch.io/deep-space-exploitation/devlog/945428/9-pathfinding
Comments
Article URL: https://lemmy.ml/post/30100312
Comments URL: https://news.ycombinator.com/i
Article URL: https://blog.cloudflare.com/web-bot-auth/
Comments URL: https://
LiveSplat is a system for turning RGBD camera streams into Gaussian splat scenes in real-time. The system works by passing all the RGBD frames into a feed forward neural net that outputs the curre
Article URL: https://github.com/marv1nnnnn/llm-min.txt
Comments URL: https://
Article URL: https://eoinmurray.info/boltzmann-machine
Comments URL: https://
