Linguists use the Bible to develop language technology for small languages

September 8, 2015, University of Copenhagen
Linguists use the Bible to develop language technology for small languages

If you speak English or another big language, you can talk to your mobile phone, use search engines, and get machine translation systems to do your translations for you. This has been made possible because English is a huge language with a great number of resources that linguists employ to develop language technology. People who speak Faroese, Welsh or Galician are less fortunate.

"When we develop systems and search engines, we usually feed huge amounts of manually annotated texts that contain information about the function and meaning of individual words into a computer. For historical reasons, these texts have primarily been newspaper articles in English and other big languages. We do not have access to similarly annotated texts in smaller languages like Faroese, Welsh, Galician and Irish, or even a major African like Yoruba which is spoken by 28 million people," says Professor Anders Søgaard from the University of Copenhagen.

Anders Søgaard and his colleagues from the project LOWLANDS: Parsing Low-Resource Languages and Domains are utilising the texts which were annotated for big languages to develop language technology for smaller languages, the key to which is to find translated texts so that the researchers can transfer knowledge of one language's grammar onto another language:

"The Bible has been translated into more than 1,500 languages, even the smallest and most 'exotic' ones, and the translations are extremely conservative; the verses have a completely uniform structure across the many different languages which means that we can make suitable computer models of even very small languages where we only have a couple of hundred pages of biblical text," Anders Søgaard says and elaborates:

"We teach the machines to register what is translated with what in the different translations of biblical texts, which makes it possible to find so many similarities between the annotated and unannotated texts that we can produce exact computer models of 100 different languages - languages such as Swahili, Wolof and Xhosa that are spoken in Nigeria. And we have made these models available for other developers and researchers. This means that we will be able to develop language technology resources for these languages similar to those which speakers of languages such as English and French have."

Anders Søgaard and his colleagues have recently presented their results in the article '"If you all you have is a bit of the Bible' at the prestigious conference Annual Meeting of the Association of Computational Linguistics.

Wikipedia as universal dictionary

The user-driven online encyclopaedia Wikipedia has also proved to be a highly useful source for the researchers who use its texts to develop language resources for languages where people do not have access to the new language technologies. Wikipedia contains over 35 million articles, but it is the fact that as many as 129 languages are represented by more than 10,000 articles each that the researchers find interesting as many articles concern the same concepts and topics.

"This allows us to do what we call 'inverted indexing' which means that we use the concept that the Wikipedia articles is about to describe the words used in the articles on the concept in different languages. We usually use the words to describe the concept but here we do it in reverse order," Anders Søgaard explains and continues:

"If the English word 'glasses' appears in the English Wikipedia entry on Harry Potter, and the German word 'Brille' is used in the equivalent German entry, it is very likely that the two words will be represented in a similar fashion in our models which form the basis of e.g. machine translation systems. And the advantage of this model is that it can be applied to 100 at the same time, including many languages that have previously been denied the language technology resources that we use every day."

The method is described in the article 'Inverted indexing for cross-lingual NLP' which Anders Søgaard wrote together with researchers from Google London. The article was also presented at the Annual Meeting of the Association of Computational Linguistics.

Explore further: Google adds 20 languages to instant translation app

More information: Annual Meeting of the Association of Computational Linguistics:

Related Stories

Grammar: Eventually the brain opts for the easy route

August 13, 2015

Languages are constantly evolving—and grammar is no exception. The way in which the brain processes language triggers adjustments. If the brain has to exert itself too much to cope with difficult case constructions, it ...

How language gives your brain a break

August 3, 2015

Here's a quick task: Take a look at the sentences below and decide which is the most effective. (1) "John threw out the old trash sitting in the kitchen." (2) "John threw the old trash sitting in the kitchen out."

Recommended for you

Nanoscale Lamb wave-driven motors in nonliquid environments

March 19, 2019

Light driven movement is challenging in nonliquid environments as micro-sized objects can experience strong dry adhesion to contact surfaces and resist movement. In a recent study, Jinsheng Lu and co-workers at the College ...

OSIRIS-REx reveals asteroid Bennu has big surprises

March 19, 2019

A NASA spacecraft that will return a sample of a near-Earth asteroid named Bennu to Earth in 2023 made the first-ever close-up observations of particle plumes erupting from an asteroid's surface. Bennu also revealed itself ...

The powerful meteor that no one saw (except satellites)

March 19, 2019

At precisely 11:48 am on December 18, 2018, a large space rock heading straight for Earth at a speed of 19 miles per second exploded into a vast ball of fire as it entered the atmosphere, 15.9 miles above the Bering Sea.

Revealing the rules behind virus scaffold construction

March 19, 2019

A team of researchers including Northwestern Engineering faculty has expanded the understanding of how virus shells self-assemble, an important step toward developing techniques that use viruses as vehicles to deliver targeted ...

Levitating objects with light

March 19, 2019

Researchers at Caltech have designed a way to levitate and propel objects using only light, by creating specific nanoscale patterning on the objects' surfaces.

1 comment

Adjust slider to filter visible comments by rank

Display comments: newest first

not rated yet Sep 08, 2015
Wow science recycles sewage and now even religion

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.