Propagating machine translation traits to predict potential impact on the target language

Abstract

Research suggests that the texts produced using machine translation (MT) do not fully represent the linguistic traits of the natural language. Yet, the ever-increasing quality and access to MT is resulting in its steady adoption by both language professionals and general users. According to contact linguistic theories, such adoption might result in MT-specific language traits permeating the target languages. This work takes a first step into considering the changes that a language might endure over time by observing the variation of linguistic trends along a series of MT generations. We train ten sequential engines using each to produce the target side of the training corpus of the following and calculate a number of metrics to observe linguistic diversity at a lexical, morphological, and syntactic level for a large, fixed test set. Quantitative results show an initial loss of lexical diversity, which, albeit gradually, only continues at a much slower pace in the following MT generations. In turn, structural variations and, in particular, morphological variations across generations are less marked, which might indicate a more stable behaviour regarding grammatical consistency. Overall, the resulting MT language seems increasingly homogeneous, marked by the reduced presence or disappearance of low-frequency words, and compact, with a decreasing proportion of function words relative to content words.