An attempt at parallelizing Machine Translation problems on a GPU. We implement a version of Rapp's "Automatic identification of word translations from unrelated English and German corpora" and attempt to parallelize the Vector calculations using PyCUDA.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
DATA
DICT
PROCESSED
WORDS
gutenbergPreprocessing
.gitignore
README
data.py
fVectors.py
graph.png
make.pdf.script
mcca.py
paper.bib
paper.tex
parallelmcca.py