parallel word embedding
train data set: http://ai.stanford.edu/~amaas//data/sentiment/, a movie review corpus.
test: test data set.
proposal: project proposal, including literature review and motivation.
final_report: final report, including details of word embedding system.
src: source code. Large_Scale_Word2Vector.py: main program, usage refers to final_report. build_vocb.py: build vacabulary table. evaluate.py: stand alone evaluation program.