This package contains CSV files with human judgments on quality of machine translation of paragraphs submitted to the WMT evaluation campaign between years 2014 and 2016.
The human judgments were collected for the following translation directions: English to Czech, English to French, English to German, and English to Russian.
For each language pair there are two annotation files. Files *_all.csv contain randomly sampled paragraphs pairs, files *_good_bleu.csv contain paragraphs sampled from outputs of systems that received BLEU score. More details on the paragraph selection and annotation process can be found in Section 4 of the paper. The files contain only those paragraphs where at least two annotators agreed.
THE LINDAT/CLARIN PROJECT (LM2015071 and CZ.02.1.01/0.0/0.0/16_013/0001781; formerly LM2010013) IS FULLY SUPPORTED BY THE MINISTRY OF EDUCATION, SPORTS AND YOUTH OF THE CZECH REPUBLIC UNDER THE PROGRAMME LM OF "LARGE INFRASTRUCTURES".
Copyright (c) 2018 UFAL MFF UK. All rights reserved.