Researchers use data from the Bible to develop AI-based text translations | HT Tech

Researchers use data from the Bible to develop AI-based text translations

Using data from the Bible, a team from the Dartmouth College developed an algorithm trained on various versions of the sacred texts that can convert written works into different styles for different audiences.

By: INDO ASIAN NEWS SERVICE
| Updated on: Oct 25 2018, 13:15 IST
This is not the first parallel dataset created for style translation. But it is the first that uses the Bible.
This is not the first parallel dataset created for style translation. But it is the first that uses the Bible. (Getty Images/iStockphoto)
This is not the first parallel dataset created for style translation. But it is the first that uses the Bible.
This is not the first parallel dataset created for style translation. But it is the first that uses the Bible. (Getty Images/iStockphoto)

Besides being a source of spiritual guidance for many people around the globe, the Bible can also help improve computer-based text translators, researchers say.

Using data from the Bible, a team from the Dartmouth College, New Hampshire in the US, developed an algorithm trained on various versions of the sacred texts that can convert written works into different styles for different audiences.

The team saw in the Bible "a large, previously untapped dataset of aligned parallel text."

"The English-language Bible comes in many different written styles, making it the perfect source text to work with for style translation," said lead author Keith Carlson, a doctoral student at Dartmouth.

According to the study, 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.

Beyond providing infinite inspiration, 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 target verses for machine-learning training sets.

It is already thoroughly indexed by the consistent use of book, chapter and verse numbers. The predictable organisation of the text across versions eliminates the risk of alignment errors that could be caused by automatic methods of matching different versions of the same text, the researchers noted.

"The Bible is a 'divine' data set to work with to study this task," said Daniel Rockmore, Professor of computer science at Dartmouth.

The team used 34 stylistically distinct Bible versions ranging in linguistic complexity from the "King James Version" to the "Bible in basic english."

The texts were fed into two algorithms -- a statistical machine translation system called "Moses" and a neural network framework commonly used in machine translation, "Seq2Seq."

Other texts that have been used in the past, ranging from Shakespeare to Wikipedia entries, provide data sets that are either much smaller or not as well suited for the task of learning style translation.

"Humans have been performing the task of organizing Bible texts for centuries, so we didn't have to put our faith into less reliable alignment algorithms," Rockmore said.

Catch all the Latest Tech News, Mobile News, Laptop News, Gaming news, Wearables News , How To News, also keep up with us on Whatsapp channel,Twitter, Facebook, Google News, and Instagram. For our latest videos, subscribe to our YouTube channel.

First Published Date: 25 Oct, 13:15 IST
NEXT ARTICLE BEGINS