While computer services are already widely available to translate words between two languages, the researchers aim to solve the "machine translation problem where the source language and target language are simply different textual styles".
Thirty-four versions of the Bible and two machine learning tools were used to develop a new system that can automatically convert written works into different styles for different audiences.
Professor Daniel Rockmore of Dartmouth College, New Hampshire who was one of the team members said in the study that they saw in the Bible "a large, previously untapped dataset of aligned parallel text".
According to the research published in the journal Royal Society Open Science, this is not the first parallel dataset created for style translation, but it is the first that uses the Bible.
Keith Carlson, a PhD student at Dartmouth and lead author of the research paper about the study said: "The English-language Bible comes in many different written styles, making it the perfect source text to work with for style translation."
The team used 34 Bible versions ranging from the King James Version to the Bible in Basic English.
The texts were then fed into two systems - a statistical machine translation system called Moses that compared texts and a neural network framework commonly used in machine translation called Seq2Seq.
Stay up to date with the latest news stories from a Christian perspective. Sign up to our daily newsletter and receive more stories like this straight to your inbox every morning.
