Given the current maturity of Machine Translation (MT), demonstrated by its growing adoption by industry (where it is mainly used to assist with the translation of technical documentation), we believe now is the time to assess the extent to which MT is useful to assist with translating literary text. Our empirical methodology relies on the fact that the applicability of MT to a given type of text can be assessed by analysing parallel corpora of that particular type and measuring (ⅰ) the degree of freedom of the translations (how literal are the translations) and (ⅱ) the narrowness of the domain (how specific or general that text is). Hence, we tackle the problem of measuring the translatability of literary text by comparing the degree of freedom of translation and domain narrowness for such texts to texts in two other domains which have been widely studied in the area of MT: technical documentation and news. Moreover, we present a pilot study on MT for literary text where we translate a novel between two Romance languages. The automatic evaluation results (66.2 BLEU points and 23.2 TER points) would be considered, in an industrial setting, as extremely useful for assisting human translation.
展开▼