Key points are not available for this paper at this time.
We explore the feasibility of applying machine (MT) to the translation of literary. To that end, we measure the translatability of literary texts by analysing parallel and measuring the degree of freedom the translations and the narrowness of the. We then explore the use of domain to translate a novel between two related languages, Spanish and Catalan. This the first time that specific MT systems are to translate novels. Our best system outperforms a strong baseline by 4. 61 absolute (9. 38% relative) in terms of BLEU and corroborated by other automatic evaluation. We provide evidence that MT can useful to assist with the translation of novels between closely-related languages, namely (i) the translations produced by our best system are equal to the ones produced by a professional human translator in almost 20% of with an additional 10% requiring at most5 character edits, and (ii) a complementary human evaluation shows that over 60% of the are perceived to be of the same (or higher) quality by native speakers.
Toral et al. (Thu,) studied this question.