We hypothesize that parallel corpora as well as machine translation
outputs contain many literal translations that are the result of transferring the con-
structions of the source language to the target language. When translating passive
expressions from English to Spanish, there are several constructions available, how-
ever, both automatic and human (if of low quality) translations tend to select the
periphrastic structure, which is the literal construction. The objective of this article
is to make use of strategies trained on monolingual corpora to translate English pas-
sive expressions into Spanish so as to verify whether unsupervised translation with
monolingual corpora benefits syntactic diversity. Special attention will be given to
the monolingual-based strategy relying on dependency-based contextualization. The
results of the experiments carried out show that the methods relying on monolingual
corpora tend to offer more non-literal translations (middle-voice) than those trained
on parallel corpora.
Keywords: Semantic Contextualization, Similarity, Unsupervised Machine Translation, Passive Voice.