Extending the Vocabulary of Fictional Languages using Neural Networks
This work addresses a niche problem for creators and fans of fictional languages in media, but it is incremental as it applies existing methods to a new domain.
The authors tackled the problem of incomplete vocabularies in fictional languages by proposing a deep learning solution that generates new words using style transfer and machine translation tools, resulting in an extended vocabulary while maintaining the creator's style.
Fictional languages have become increasingly popular over the recent years appearing in novels, movies, TV shows, comics, and video games. While some of these fictional languages have a complete vocabulary, most do not. We propose a deep learning solution to the problem. Using style transfer and machine translation tools, we generate new words for a given target fictional language, while maintaining the style of its creator, hence extending this language vocabulary.