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

Join the newsletter!

Error: Please check your email address.
Rocket to Success - Your 10 Tips for Smarter ERP System Selection

Tags internetInternet-based applications and servicesUniversity of Amsterdam

Keep up with the latest tech news, reviews and previews by subscribing to the Good Gear Guide newsletter.

Loek Essers

IDG News Service
Show Comments

Cool Tech

SanDisk MicroSDXC™ for Nintendo® Switch™

Learn more >

Breitling Superocean Heritage Chronographe 44

Learn more >

Toys for Boys

Family Friendly

Panasonic 4K UHD Blu-Ray Player and Full HD Recorder with Netflix - UBT1GL-K

Learn more >

Stocking Stuffer

Razer DeathAdder Expert Ergonomic Gaming Mouse

Learn more >

Christmas Gift Guide

Click for more ›

Most Popular Reviews

Latest Articles

Resources

PCW Evaluation Team

Edwina Hargreaves

WD My Cloud Home

I would recommend this device for families and small businesses who want one safe place to store all their important digital content and a way to easily share it with friends, family, business partners, or customers.

Walid Mikhael

Brother QL-820NWB Professional Label Printer

It’s easy to set up, it’s compact and quiet when printing and to top if off, the print quality is excellent. This is hands down the best printer I’ve used for printing labels.

Ben Ramsden

Sharp PN-40TC1 Huddle Board

Brainstorming, innovation, problem solving, and negotiation have all become much more productive and valuable if people can easily collaborate in real time with minimal friction.

Sarah Ieroianni

Brother QL-820NWB Professional Label Printer

The print quality also does not disappoint, it’s clear, bold, doesn’t smudge and the text is perfectly sized.

Ratchada Dunn

Sharp PN-40TC1 Huddle Board

The Huddle Board’s built in program; Sharp Touch Viewing software allows us to easily manipulate and edit our documents (jpegs and PDFs) all at the same time on the dashboard.

George Khoury

Sharp PN-40TC1 Huddle Board

The biggest perks for me would be that it comes with easy to use and comprehensive programs that make the collaboration process a whole lot more intuitive and organic

Featured Content

Product Launch Showcase

Latest Jobs

Don’t have an account? Sign up here

Don't have an account? Sign up now

Forgot password?