GitHub - accurat-toolkit/EMACC: A textual unit aligner for comparable corpora using Expectation-Maximization.

accurat-toolkit / EMACC Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

A textual unit aligner for comparable corpora using Expectation-Maximization.

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
dict		dict
res		res
test		test
README		README
cluster.info		cluster.info
emacc2.pl		emacc2.pl
emaccconf.pm		emaccconf.pm
hddmatrix.pm		hddmatrix.pm
precompworker.pl		precompworker.pl

Repository files navigation

To do a quick test-run, just issue (from this directory) the command:

perl emacc2.pl --source en --target ro --input test\doclist-en.txt --input test\doclist-ro.txt --output test-alignment.txt

In Windows, be sure to configure the file 'cluster.info' and 'emaccconf.pm' first! Especially if you have a lot of documents to align!
In Windows it is advisable to run EMACC under Cygwin.

For more details, please read ACCURAT D2.6 deliverable, Version 2.