search

artetxem / vecmap

A framework to learn cross-lingual word embedding mappings
GNU General Public License v3.0
645 stars 130 forks source link

Is that true the source and target embedding space should have the same dimensionality? #2

Open yuchenlin opened 7 years ago

yuchenlin commented 7 years ago

Hi Mikel,

I found that you didn't mention the case that the source embeddings and target embeddings can have different dimensionality (for example, english 300d, and Chinese 100d). Did I miss something in the paper or the code? Or you only focus on the situation that the two embedding spaces must have the same dimensionality?

Thanks and regards, Bill

artetxem commented 7 years ago

You are right, we currently do not support both spaces having different dimensionality. It should not be difficult to implement it, but I do not think that it would be particularly useful either. I will leave the issue open for now.

shizhediao commented 6 years ago

what if the source embedding is 200000300 while the target embedding is 199999300, could it be trained correctly by this code? thanks!

shizhediao commented 6 years ago

@artetxem

artetxem commented 6 years ago

@shizhediao that should work ok.