When minority and local languages are lost, national security suffers: not only are significant increases in substance abuse, suicide, and assault often documented, a void is created that has been historically been exploited by adversaries. For example, tens of millions from minority language communities ahistorically assume the Russian language and/or identity as their own in Ukraine, Belarus, NATO allies, and even the United States. If native language communication gaps remain in the hands of adversaries only, using their long experience with these languages, NATO remains at a major disadvantage attempting to engage these communities. In Europe, psychic wounds inflicted in part by language loss have not been closed by assimilation. Instead, cities experience bursts of isolating tensions in the West and Eastern populations are convinced by adversarial powers that those powers are their true allies, who understand and respect them. Nor is education in the national language a panacea: in the case of Ukraine (and even Spain), non-trivial differences between local lects and the official language create openings for adversaries to fan the flames of separatism.
Using machine translation engines to empower NATO and its partners in training recruits or acting on the ground in the language closest to their hearts and minds can win immediate ‘us’-ness and showcase NATO’s embraced polycultural vision. In this experiment, custom engines were crafted to translate between the official language of Poland and that of its indigenous Lemko minority, whose language has been subjected to centuries-long hostile power influence and interference. In a first, engines were scored translating from Lemko to Polish using metrics developed with support from DARPA: a bilingual evaluation understudy (BLEU) score of 31.13 and translation edit rate (TER) of 54.10. Meanwhile, in the other direction, the engines scored TER 53.73 and BLEU 29.49, a score 6.5 times better than that of Google Translate’s Polish-Ukrainian service.
Keywords
CULTURE, EMERGING TECHNOLOGIES, NATURAL LANGUAGE PROCESSING
Additional Keywords
Lemko, Machine Translation, Ukrainian