Incorporating Human Translator Style into English-Turkish Literary Machine Translation
This addresses the problem of stylistic adaptation in literary machine translation for translators and researchers, though it is incremental as it builds on pre-trained models.
The paper tackled adapting machine translation to literary domains by incorporating human translator style into English-Turkish models, showing that style can be highly recreated in target translations through fine-tuning on manually-aligned works.
Although machine translation systems are mostly designed to serve in the general domain, there is a growing tendency to adapt these systems to other domains like literary translation. In this paper, we focus on English-Turkish literary translation and develop machine translation models that take into account the stylistic features of translators. We fine-tune a pre-trained machine translation model by the manually-aligned works of a particular translator. We make a detailed analysis of the effects of manual and automatic alignments, data augmentation methods, and corpus size on the translations. We propose an approach based on stylistic features to evaluate the style of a translator in the output translations. We show that the human translator style can be highly recreated in the target machine translations by adapting the models to the style of the translator.