Most European languages in danger of digital extinction

Sep 25, 2012

Scientists from The University of Manchester were part of a European team of researchers who concluded that digital assistance for 21 of the 30 languages investigated is 'non-existent' or 'weak' at best.

The report coincides with the European Day of Languages [September 26], a day which recognises the importance of fostering and developing the rich linguistic and of our continent.

Languages spoken by a small number of people could be at risk because they do not have technological support, the report by META-NET, a European network of excellence that consists of 60 research centres in 34 countries, including the University of Manchester's National Centre for Text Mining (NaCTeM), found.

Icelandic, Latvian, Lithuanian and Maltese are at the highest risk of disappearing, while other languages such as Bulgarian, Greek, Hungarian and Polish are also at risk. The researchers claim that 21 out of 30 European languages could become extinct in the digital world.

The study, prepared by more than 200 experts and documented in 30 volumes of the META-NET White Paper Series, assessed technology support for each language in four different areas: automatic translation, speech interaction, text analysis and the availability of language resources.

Several languages, for example Icelandic, Latvian, Lithuanian and Maltese, receive this lowest score in all four areas.

While English has the best language technology support amongst all European languages, it can still not be considered as "excellent support", but rather only "good support", the University of Manchester researchers found in the White Paper for English.

Dutch, French, German, Italian and Spanish are considered to have "moderate support". Languages such as Basque, Bulgarian, Catalan, Greek, Hungarian and Polish exhibit "fragmentary support", which also places them in the set of high-risk languages.

Language technology software is used to process spoken or written . Well-known examples include spelling and grammar checkers, interactive personal assistants on smartphones (such as Siri on the iPhone), dialogue systems that work over the phone, systems and web search engines.

The lack of available software for the high-risk languages means that without drastic action, they will be unable to survive in today's digital world.

Language technology systems primarily rely on statistical methods that require incredibly large amounts of written or spoken data - difficult to acquire for languages with relatively few speakers.

Furthermore, statistical language technology systems have inherent limits on their quality, as can be seen, for example, in the often amusing incorrect translations produced by online machine translation systems.

The report concludes that a coordinated, large-scale effort has to be made in Europe to create the missing technologies and transfer this technology to the languages faced with digital extinction .

Professor Sophia Ananiadou, director of NaCTeM, said: "In the UK, most of us use software that incorporates language technology without even realising it.

"Language technology already makes our lives easier and has huge potential to help us in many different ways. As digital information and communication is becoming increasingly dominant, it is vital that sophisticated language technology support is available for a wider range of languages, otherwise collaboration with our European neighbours will become more difficult."

Professor Hans Uszkoreit, coordinator of META-NET, said: "The results of our study are most alarming. The majority of European languages are severely under-resourced and some are almost completely neglected. In this sense, many of our languages are not yet future-proof.

Explore further: When identity marketing backfires: Consumers don't like to be told what they like

add to favorites email to friend print save as pdf

Related Stories

Google translates more India languages

Jun 21, 2011

Google on Tuesday expanded its free Internet translation service to include five languages spoken by more than a half million people in India and Bangladesh.

Indo-European languages originate in Anatolia

Aug 28, 2012

(Phys.org)—The Indo-European languages belong to one of the widest spread language families of the world. For the last two millenia, many of these languages have been written, and their history is relatively ...

Recommended for you

Online reviews: When do negative opinions boost sales?

17 hours ago

When purchasing items online, reading customer reviews is a convenient way to get a real-world account of other people's opinions of the product. According to a new study in the Journal of Consumer Research, negative review ...

User comments : 1

Adjust slider to filter visible comments by rank

Display comments: newest first

Sean_W
1 / 5 (1) Sep 25, 2012
Not that there would be no benefit to increased language technologies for European languages, the fact that Europe--like most of the planet--is undergoing an economic meltdown is likely to make this a low priority.

More news stories

Online reviews: When do negative opinions boost sales?

When purchasing items online, reading customer reviews is a convenient way to get a real-world account of other people's opinions of the product. According to a new study in the Journal of Consumer Research, negative review ...

Making 'bucky-balls' in spin-out's sights

(Phys.org) —A new Oxford spin-out firm is targeting the difficult challenge of manufacturing fullerenes, known as 'bucky-balls' because of their spherical shape, a type of carbon nanomaterial which, like ...