qe-team / marmot

MARMOT - the open source framework for feature extraction and machine learning, designed to estimate the quality of Machine Translation output
ISC License
21 stars 7 forks source link

binarizing alignment features takes a long time #22

Closed chrishokamp closed 9 years ago

chrishokamp commented 9 years ago

why does this take so long? Is it just because there are so many possible values? what is the bottleneck in the process?

varvara-l commented 9 years ago

I don't know. There are similar complaints (http://stackoverflow.com/questions/20158624/labelbinarizer-takes-forever). But when there are many values, it should just take much space, not time.

chrishokamp commented 9 years ago

Ok let's close for now - I think part of it was the bug we fixed yesterday