A team of researchers are using artificial intelligence to revolutionize the world of Bible translation, thanks to a groundbreaking project known as the “Greek Room.”
Spearheaded by Ulf Hermjakob, a senior research scientist at the University of Southern California’s Information Sciences Institute, and Joel Mathew, a research engineer at ISI, this initiative utilizes cutting-edge technology to translate the Bible into languages lacking a written version of Scripture.
Bible translation has traditionally been a laborious and time-consuming process, and can often take over a decade to complete. Out of the world’s 7,100 languages, only about 700 possess a complete copy of the Bible. While more than 3,500 languages have at least one book of the Bible, over 6,000 languages lack a comprehensive version.
“People don’t realize that there are about 7,100 languages in the world,” Hermjakob explained. “Google Translate covers about 100 of them. Our focus for this Bible translation is on very low-resource languages that don’t even fall within the top 500.”
Mathew, whose parents were involved in Bible translation in his home country of India, believes that technology could improve all areas of the process.
“There were a lot of areas where I felt software technology could really speed up, improve, support and help them,” Mathew said. “It’s one of my passions to see the Bible translated in all languages.”
The Greek Room project aims to develop tools that enhance the efficiency of Bible translation. While certain aspects of translation are objective and leave little room for debate, other parts require human intervention due to their subjective nature. Mathew highlights the challenge of translating concepts that do not easily align with local languages.
“There is a community living in the mountains, and they live in huts without doors, so there’s no concept of a door in their culture,” Mathew explained. “In the Bible, there is a verse that says, ‘Behold I stand at the door and knock.’ The question is, how do you translate that for people so that it is meaningful to them?”
In response to such hurdles, the Greek Room project allows translators to dedicate more time to subjective aspects. Mathew clarifies their approach: “We try to then explain it as not specifically knocking at the door, but instead describe a scene where someone is standing at the entrance of your house and asking to be invited to come in.”
Driven by their shared passion for Bible translation, Hermjakob and Mathew aspire to make the Greek Room an open-source platform accessible to translators worldwide.
“We want to make it so that other Bible translation efforts can use what we have built in for their own research as well, so one thing we decided early on is that we want to make our data and code public,” Hermjakob said.