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