Nowadays models are able to handle vocabularies from multiple languages. If two words have pretty similar meanings in different languages, they might have similar embeddings as well. One follow-up question is, if the words have multiple meanings, and one of the meanings is pretty similar but others are not, will the embedding still be similar?
If you are inspired by this idea, you can reach out to the authors for collaboration or cite it:
@misc{chen-do-words-with-2026,
author = {Chen, Mike},
title = {Do words with similar meanings in different languages have similar embeddings},
year = {2026},
url = {https://hypogenic.ai/ideahub/idea/GBXyrHRKdBOZl28EvL46}
}Please sign in to comment on this idea.
No comments yet. Be the first to share your thoughts!