vecmap
vecmap copied to clipboard
artetxem
A framework to learn cross-lingual word embedding mappings
In other words, one cannot search for OOV words after mapping..
Dear Mikel, first of all congratulations on this great piece of work and thank you for sharing it with the community. I experienced out-of-memory errors when mapping pre-trained fastText embeddings...
 I tried to follow the steps to run the code ,however when I input "python3 map_embeddings.py --supervised en-es.train.txt es.emb.txt en.emb.txt SRC_MAPPED.EMB TRG_MAPPED.EMB -cuda" and run it, no results returned.
Recently when I was trying vecmap using following command !python3 map_embeddings.py --unsupervised wiki.sa.vec.txt wiki.kn.vec.txt SRC_MAPPED.EMB TRG_MAPPED.EMB I observed that this command is creating only SRC_MAPPED.EMB file. TRG_MAPPED.EMB was empty by...
UnicodeEncodeError: 'utf-8' codec can't encode character '\udcf6' in position 0: surrogates not allowed
Hi, I'm trying to learn the cross-lingual n-gram embedding using [phrase2vec](https://github.com/artetxem/phrase2vec) and vecmap, like your previous work (https://www.aclweb.org/anthology/D18-1399.pdf). Is it possible to use the phrase table in this case? In...
I ran the code on my dataset, and the objective I got is 32.5354% after 67 iteration. It is normal? How should I finetune the parameters?
hey! How can I export the dictionary(for most frequent 1000 words) after alignment using a fully unsupervised method? Thank you in advance.
I'm running the below command, however my results are not deterministic. Is there a way to do so? (I'm debugging the pipeline, so would like a fully reproducible run) ```...
Dear Mikel, Thank you for sharing your great work with us. I'm running your codes and trying to reproduce the result that you reported in your ACL 2018 paper. But...
