40  Last view: 2024-07-283  Last update: 2018-01-23

WMT 2015 Test Sets

http://www.statmt.org/wmt15/

These are the test sets for the WMT shared translation task. They are small parallel data sets used for testing MT systems, and are typically created by translating a selection of crawled articles from online news sites. The core languages are German-English and Czech-English; other guest language pairs will be introduced in each year. For 2015 the guest language was Romanian. We also included Russian, Turkish and Finnish, with funding from other sources. The source data are crawled from online news sites and carry the respective licensing conditions.