Face-to-Face with the World – Skype’s Translator

3 06 2015

Skype has invited its users to try a “Preview” version of their Translator product and provide feedback. The program is available for face-to-face, real-time audio/video conversations in four languages so far: English, Spanish, Mandarin and Italian, with more on the way. Instant Messaging (IM) is available in over 45 languages, from Dutch to Hindi to Klingon.

Developed by Microsoft, Skype Translator requires Windows 8 and up, and its translation quality has been compared to that of Babel Fish and Google Translate. Skype’s blog states that they have been “investing in speech recognition, automatic translation and machine learning technologies for more than a decade.”

Nearly as important as the Bing Translator algorithm Skype Translator relies on, is the voice recognition component that initiates and completes the transformation of a speaker’s words into something in the target language that is understandable on the other end. The Translator first turns spoken words to text, then uses machine learning to interpret the grammar, and statistical matching within a text database to pin down meanings. That “written” translation is then funneled back through voice recognition software and “Jane” or “Bob” – the female and male Skype AI (Artificial Intelligence) voices – deliver what Skype hopes to be a pleasant, human-like audio expression of the speaker’s meaning.

Microsoft’s research into deep “artificial neural networks” (ANNs) in the early 2000’s led to the AI that makes all of this possible. ANNs are sets of statistical learning algorithms that create a responsiveness to input that resembles the experienced-based development of the human mind, thus enabling “understanding” of complex systems such as language. It was this work that led to what Wired Magazine calls “Skype’s most startling breakthrough: the ability to reliably recognize almost anybody’s speech,” including the interpretation of rhythm and intonation.

There is also a more controversial issue that Skype and Microsoft have made some preliminary choices about: certain elements are “scrubbed” from translations, that is, they are not acknowledged or translated at all. Repetitive speech tics and profanity, for example. Therefore, in essence Skype Translator currently does a bit of conversation editing, which could feel like censoring. This will undoubtedly become one of the areas that Skype Translator users will give feedback about over time as they utilize the program to personalize their global communication.

J. McShulskis


Machine Translation is not Google Translate

5 03 2014

Google Translate is one of the most popular instant translation systems available online, and while it is certainly a type of “machine translation,” it’s quite a different tool than those used in certain situations by professional language service providers (LSPs)such as Skrivanek.

google-translateTo generate translations, Google Translate (GT) searches millions of sentences for comparable patterns in origin- and target-language documents that have already been translated by human translators and entered into its database. Then, basically, it makes an “educated” guess as to what an appropriate translation would be. This process of seeking patterns in large amounts of text is called “statistical machine translation” (SMT).

You’ve probably seen how GT works: type in words and you will receive a quick translation (in any of 80 languages) that will range in quality from excellent to questionable, depending on how much text for your language pairing has been fed into the GT database. Google Translate director, German computer scientist Franz Josef Och, describes the GT process as the computation of “probabilities of translation” through comparison of the submitted text with billions of words of “learned” text in GT. The more text is available in the database, the “smarter” GT becomes. Tellingly, the GT creative team is made up of mathematicians and programmers and does not include any linguists.*

On the other hand, software systems such as PROMT, Asia Online, SYSTRAN and Moses, referred to as Machine Translation (MT), are complex, customizable translation engines that are specifically trained for certain projects or content in order to maximize efficiency and accuracy. Often used for technical and repetitive texts without subtleties, MT can assist large corporations in the translation of materials they simply would not have the capacity or budget for otherwise.

In the past MT systems were often entirely “rules based” (RBMT), meaning that information about language structures – not mathematical formulas – formed the foundation of their programming. Now MT engines like those mentioned above are often hybrid systems that combine RBMT and SMT. Basically, MT engineers “train” the sophisticated MT programs with glossaries from relevant fields, along with text from specific documents and corrections from previous mistakes, resulting in a tool that becomes more refined the more it is used for each client. This kind of multi-faceted MT requires extremely high levels of capital investment for both hardware and software, and for the process of customization.

Instant online translation tools like Google Translate are a gift in an era of communication expansion so extensive that a large American corporation might want immediate access to comments tweeted by an Icelandic teenager about its latest product. There are numerous instances of such social and commercial interaction online when communication speed is more important than language precision.

But for linguistically and culturally accurate translations of text that contains any ambiguities, nuances or critical information, hands-on human intelligence is still essential. Even complex MT systems are most appropriate for only some types of texts and then merely as producers of raw output that is checked, smoothed and corrected by human post-editors.

For further information:

*”Google Translate Has Ambitious Goals for Machine Translation,” by Thomas Schulz, Spiegel Online, Spiegel.de, September 2013

J. McShulskis

Do you think Machine Translation will replace human translation in time?

27 11 2013