Believers turn to the scriptures for solace and spiritual guidance, but researchers at Dartmouth College have turned to the Bible for a different reason. They have used the holy book to improve translations done by computers.
How? The Bible (along with its versions) is a repository of an enormous amount of data, and algorithms improve when they get more data to train on. Using the data in the Bible, the researchers developed an algorithm that trained on various versions of the book and can now convert written works into different styles without losing the context of the text and understanding idiomatic expressions.
Researchers are increasingly striving to help machines translate words from one language to another the way professional translators would. This implies that machines must understand the context of words and sentences, and make sense of idioms, phrases and jokes.
However, despite the fact that billions of words are being translated daily by multilingual machine translation services such as Google Translate, Microsoft Translator and Systran’s Pure Neural Machine Translator, machines have a long way to go before they can function as fluently as humans do.
The Dartmouth research team saw in the Bible “a large, previously untapped data set of aligned parallel text (or translation/s),” according to a 23 October press statement by the university. For instance, each version of the Bible contains more than 31,000 verses that the researchers used to produce over 1.5 million unique pairings of source and translated verses for machine learning training sets.