This repository contains the data gathered through experimentation, and the analysis performed for our paper. We also include the sources for our paper, and presentation.
README.md: this file.
exported-tasks-2014-11-25.ver4.xml (raw data) data-4.1+trans.dat (preprocessed data) wmt12.RNK_results.filtered.human.noties (human eval scores) wmt12.spanish_quality (translations selected based on their quality)
lib.R (general R functions) wmt15_time_final.R (code for reproducing analysis)
F. Guzman, A. Abdelali, H. Sajjad, I. Temnikova, and S. Vogel, "How do Humans Evaluate Machine Translation", The Proceedings of the Tenth Workshop on Statistical Machine Translation WMT2015. 17-18 September 2015, Lisbon, Portugal [PDF] [BibTeX]
If you have any question about the corpus, please direct your inquiries to Ahmed Abdelali or Francisco Guzman.
Developed by: Qatar Computing Research Institute Arabic Language Technologies Group