NIST Open Machine Translation 2012 Current Test
===============================================

This set contains the evaluation sets (source data and human reference 
translations), DTD, scoring software, and evaluation plan for the Current 
test of the NIST Open Machine Translation 2012 Evaluation.  The Current test 
consisted of two Chinese-to-English tests; one containing general Newswire and 
Web data, one limited to Web data from a restricted domain, "food".  The data 
stems from January to March 2011.

Please refer to the evaluation plan included in this package for more details.

A test set consists of two files, a source and a reference file.  Each 
reference file contains four independent human reference translations of the 
source data.

The test sets in this package are in XML format compliant with the included 
DTD.

Please contact mt_poc@nist.gov with questions.
Please visit the NIST OpenMT website, 
http://www.nist.gov/itl/iad/mig/openmt.cfm, for general information on the 
NIST OpenMT evaluations.


Package Contents
----------------

README.txt - this file

Evaluation plan:
OpenMT12_EvalPlan.pdf

Scoring utility: mteval-v13a-20091001.tar.gz

DTD: mteval-xml-v1.6.dtd

Test sets (src = source, ref = human reference translations):
Chinese-to-English general:
OpenMT12_Current_chi2eng-[src|ref].xml
Chinese-to-English restricted domain:
OpenMT12_Current_chi2eng-RestrictedDomain-[src|ref].xml


Data Set Statistics
-------------------

Data genres:
nw = newswire
wb = web data

Source				Genre	Documents	Segments	Source tokens

Chinese general			nw	45		400		18184
Chinese	general 		wb	28		420		15181

Chinese restricted domain	wb	149		2184		48422

The token counts for Chinese data are "character" counts, which were obtained 
by counting tokens matching the UNICODE-based regular expression "\w".  The Python "re" 
module was used to obtain these counts.