A Neural Approach to Language Variety Translation
This addresses translation challenges for speakers of closely related language varieties, though it is incremental as it applies existing neural methods to a new but specific domain.
The paper tackles machine translation between standard national varieties of the same language, specifically Brazilian and European Portuguese, and reports a performance improvement of 0.9 BLEU points in one direction and 0.2 in the other, with human evaluation showing preference for the neural system.
In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language. We take the pair Brazilian - European Portuguese as an example and compare the performance of this method to a phrase-based statistical machine translation system. We report a performance improvement of 0.9 BLEU points in translating from European to Brazilian Portuguese and 0.2 BLEU points when translating in the opposite direction. We also carried out a human evaluation experiment with native speakers of Brazilian Portuguese which indicates that humans prefer the output produced by the neural-based system in comparison to the statistical system.