Evaluating machine translation for assimilation via a gap-filling task
Ekaterina Ageeva, Mikel L. Forcada, Francis Morton Tyers, Juan Antonio Pérez-Ortiz · 2015
This paper provides additional observa-tions on the viability of a strategy indepen-dently proposed in 2012 and 2013 for eval-uation of machine translation (MT) for as-similation purposes. The strategy involves human evaluators, who are asked to restore keywords (to fill gaps) in reference transla-tions. The evaluation method is applied to two language pairs, Basque–Spanish and Tatar–Russian. To reduce the amount of time required to prepare tasks and analyse results, an open-source task management system is introduced. The evaluation re-sults show that the gap-filling task may be suitable for measuring MT quality for as-similation purposes. 1