Menu
Neural networks draw on context to improve machine translations

Neural networks draw on context to improve machine translations

Dutch researchers have improved the output of a statistical machine translation system by examining the context in which words are found

Researchers at the University of Amsterdam are using neural networks to help a statistical machine translation systems learn what all human translators know -- that the best translation of a word often depends on the context.

Machine translation systems such as Google Translate or those at iTranslate4.eu guess how to translate words and phrases based on how often they appear in a large corpus of human-translated texts. Such tools are increasingly important as individuals and businesses seek to access information or buy products and services from other countries where different languages are spoken.

Statistical machine translation work by breaking sentences into phrase fragments and selecting the most likely translation for each fragment -- a process that doesn't always yield the best translation for the sentence as a whole in morphologically rich languages such as those where nouns are inflected for number, case and gender.

To improve the word selection of such systems when translating into morphologically rich languages such as Russian, Bulgarian and German, the team used a neural network to analyze the words in context in the source language.

Translating sentences into grammatically more complex languages is relatively easy for human translators because they understand the grammatical function of the word in a sentence. Machine translators however find it particularly difficult to do this because word forms from a grammatically more simple language like English do not contain enough information for producing the correct version of that word into a morphologically rich language.

It is for instance, difficult for machines to translate a sentence containing an English word form like "the man" into German because the German language offers several word forms -- "der Mann", "des Mannes", "dem Mann" and "den Mann" -- that could all be correct translations, depending on the context.

The neural network is able to derive grammatical functions of words without having explicit knowledge of the grammar, said Ke Tran, one of the researchers. This means that to learn word functions the method does not depend on examples hand-picked by the researchers, which can be a difficult and costly process, especially for languages with few speakers.

The researchers reported significant word translation prediction accuracy for Bulgarian, Czech, and Russian. Moreover, preliminary results for integrating the approach into a large-scale English-Russian statistical machine translation system show small but statistically significant improvements in translation quality, they said.

In the future, the new method will be integrated in a translation system called Oister, being developed by the university. The findings will also be presented during the conference on Empirical Methods on Natural Language Processing in Doha, Qatar next week.

Loek is Amsterdam Correspondent and covers online privacy, intellectual property, online payment issues as well as EU technology policy and regulation for the IDG News Service. Follow him on Twitter at @loekessers or email tips and comments to loek_essers@idg.com


Follow Us

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.

Tags internetInternet-based applications and servicesUniversity of Amsterdam

Featured

Slideshows

Meet the leading female front runners of the Kiwi channel

Meet the leading female front runners of the Kiwi channel

Reseller News honoured the leading female front runners of the New Zealand channel at the 2018 Women in ICT Awards (WIICTA) in Auckland. The awards honoured standout individuals across seven categories, spanning Entrepreneur; Innovation; Rising Star; Shining Star; Community; Technical and Achievement.

Meet the leading female front runners of the Kiwi channel
Meet the top performing customer-centric Microsoft channel partners

Meet the top performing customer-centric Microsoft channel partners

Microsoft honoured leading partners across the channel following a year of customer innovation and market growth in New Zealand. The 2018 Microsoft Partner Awards recognised excellence within the context of the end-user, spanning a host of emerging and established providers.

Meet the top performing customer-centric Microsoft channel partners
Reseller News launches new-look Awards at 2018 Judges’ Lunch

Reseller News launches new-look Awards at 2018 Judges’ Lunch

Introducing the Reseller News Innovation Awards, launched to the channel at the 2018 Judges’ Lunch in Auckland. With more than 70 judges now part of the voting panel, the new-look awards will reflect the changing dynamics of the channel, recognising excellence across customer value and innovation - spanning start-ups, partners, distributors and vendors.

Reseller News launches new-look Awards at 2018 Judges’ Lunch
Show Comments