Microsoft Translator Team Blog

News and Views from the Microsoft Translator Team in Microsoft Research.

Visit our Forums

For questions please use Microsoft Translator technical forums. We monitor them daily!

  • Microsoft Translator Team Blog

    New language pair on MicrosoftTranslator.com

    • 14 Comments

    The Translator team is excited to announce the availability of the English to Russian language pair on MicrosoftTranslator.com.  This language pair is now available across all implementations of the translator technology, including Live Search and (in the next few days) the Windows Live Messenger TBot. 

    You have probably noticed that the Russian to English language pair has been available for some time on our site.  As always, translation quality is a top focus for our team.  Sometimes reaching quality takes longer for a particular direction – this can be for many reasons.  For example, if you are translating between a simple language and a complex language, the translations will be better going to the simple language than they will be going to the complex language.  If you are interested in learning more about the technology behind our machine translation engine, see Will Lewis’ blog post on statistical machine translation.

    While machine translation is certainly never perfect, for this new language pair we have now hit our quality bar for release.  How do we determine the quality bar?  In general, when the translation can be considered “useful”.  We consistently receive feedback from our users that imperfect translation which is useful is better than no translation.  So we have to balance user demand with translation quality.  With that in mind, we test our language pairs with human evaluations, until we have reached “useful” translation. 

    We are always open to your constructive feedback and help – please continue to help us so that we can keep improving quality!  We are always very grateful for good feedback. 

    Some other updates in this release you may notice:

    · We have officially migrated our domain to www.microsofttranslator.com

    · Improved quality across several language pairs, due to improvements in training data quality

    · Improvements in Japanese to English, due to an improved method of parsing the training data

  • Microsoft Translator Team Blog

    Linking to a foreign language web page with Microsoft Translator

    • 5 Comments

    Update: For your own pages, the Microsoft Translator webpage widget allows you to deliver the page in multiple languages, without taking your users away from the site. Go here to get the code snippet for your widget. Pages with the widget on them can be linked to in a specific language by adding #mstto=<lg> to the URL where <lg> is the language code (like es for Spanish) you want the page to be shown in.

    Have you ever wanted to link to a web page that is in a different language than your own site?  You can use Microsoft Translator to link to the translated web page, within the bilingual viewer. 

    Example of showing an English language site to a foreign language user (Simplified Chinese):

    http://www.microsofttranslator.com/bv.aspx?from=en&to=zh-chs&lo=TB&a=www.technet.com

    Example of showing an foreign language site (Japanese) to an English user:

    http://www.microsofttranslator.com/BV.aspx?from=ja&to=en&lo=TP&a=http://www.metro.tokyo.jp/

    You can directly embed all the options in the link. Here is how that works:

    Syntax (see examples above):

    http://www.microsofttranslator.com/bv.aspx?

              from=<source language>&

              to=<target language>&

              lo=<layout>&

              a=<target address>

    Valid language codes:

    en, de, fr, it, es, pt, zh-chs, zh-cht, ja, ko, ar, ru, nl, cs, da, he, el, pl, sv, th

    Valid layout codes:

    SS (side-by-side), TB (top-bottom), SP (original with hover translation), TP (translation with hover original)

  • Microsoft Translator Team Blog

    Politically Incorrect Machines

    • 11 Comments

    While we at the Machine Translation team have been seeing increasing traffic to our various offerings over the past few months, we noticed a sudden bump in traffic yesterday. Having grown up on Agatha Christie and Sherlock Holmes, such mysteries are irresistible for me – and a number of other folks on the team were just as curious to find out what caused this sudden bump. We figured that the IE8 Activity/Accelerator, the Messenger Bot, Search translations, Office translations were all showing the same upward trend as the days before and thus were not the specific reason for this bump.

    Eventually, we were able to identify one potential reason why we were seeing this spike. Our user community found an oddity in how the machine translation engine processed the translation for several names from English to German. It was to be expected that when the engine translates the name of the candidate of one party to someone from the other party, given the current political atmosphere in the run up to US elections, that it would end up as news. While we certainly welcome all the new users that came by to check this phenomenon out – we wanted to share with our users the reason why such things seem to happen from time to time with statistically trained machine translation systems from us and others.

    A Statistical Machine Translation engine is trained on lots and lots of parallel data, that is, data that exists in both a source language (e.g., English) and a target language (e.g., German), where the source and target are translations of one another. Our engine is trained on millions of sentences for each language pair we support. In order to train on a particular corpus of data—maybe a large number of newswire articles in English which have been translated into German—we first have to break that corpus down into sentences. After the corpus is sentence broken, we feed the resulting sentences into a sentence aligner, the sole purpose of which is to find what sentences on the source side align with sentences on the target side. This is no trivial task, since a sentence on one side could conceivably align with one or more sentences on the target (or possibly none at all!). The aligner will sometimes make mistakes, and misalign one sentence with another that is in fact not a translation. This can lead to some mistranslations, especially if there are words in the source and target that are infrequently occurring. Since our translation engine is statistical, it is highly reliant on co-occurrence frequencies between words in the source and target data. If certain words are infrequently occurring—people’s names, for instance, may only occur a few times across a corpus of millions of sentences—the lack of frequency can lead to mistranslations resulting from incorrect “guesses” between source and target (i.e., low probabilities assigned to particular source and target words). This can lead to some comical gaffes in our translation system.

    So, that is how the “machine” decided to translate in a way that ended up with the community attributing it to the sense of humor of our team. While we continue to work hard to ensure proper alignments, it is to be expected from a statistical system that is built on millions to billions of words that such a situation could repeat.

    The current issue with alignment should now be resolved but we urge our community of users to keep helping us identify any such situations by contacting us through this blog.

    -Vikram

    Vikram Dendi leads Business Strategy & Product Planning for the Microsoft Translator team
  • Microsoft Translator Team Blog

    Have you seen the Bilingual Viewer?

    • 18 Comments

    Our web page translation includes a user interface we refer to as the Bilingual Viewer. It offers 4 types of bilingual views which users can choose depending on preference. The side-by-side and top/bottom views offer synchronized scrolling, highlighting, and navigation. In the two single language views, you can hover your mouse pointer over a sentence in one language and the corresponding passage in the other language is automatically displayed nearby for ease of reference. Finally, we render the translated text progressively on a web page in order to make it more quickly available for the user to read, while other page elements are still being translated in the background.

    To change your view, just click on one of the four options in the “Views” section on the upper right part of the site:

    image

    Side-by-side view:

    image

    Top/Bottom view:

    image

    Original with hover translation view:

    image

    Translation with hover original view:

    image

    Note: when you click on “Translate this page” while using Live Search, the web page will be opened in the Bilingual Viewer (in side-by-side view or the view you selected during your last viewing session).  Read more about that here

    Check out the bilingual viewer today if you haven’t played around with it before!  And as always, let us know your feedback :)

  • Microsoft Translator Team Blog

    Microsoft Translator makes the Web more worldly

    • 44 Comments

    Did you know that Microsoft Translator powers translations in Live Search Bing? 

    For example, to translate this search result, click "Translate this page" at the end of the result description:

    Image of Wikipedia search result

    You'll see the page in a bilingual view, with the original page on the left, and the translated page on the right.

    Here is the list languages we support today:

    English to/from:

    Arabic   French   Latvian    Swedish
    Bulgarian  German   Lithuanian   Thai
    Chinese Simplified  Greek   Norwegian   Turkish
    Chinese Traditional  Haitian Creole   Polish   Ukrainian
    Czech  Hebrew     Portuguese   Vietnamese
    Danish  Hungarian   Romanian  
    Dutch  Indonesian   Russian  
    English  Italian   Slovak  
    Estonian  Japanese   Slovenian  
    Finnish  Korean   Spanish

    We'll roll out more languages over the next several months.

    So try clicking 'Translate this page' in your search results. Let us know what you think!

    Bing Search Blog

    Update (11/15): Edited the link to the Bing Search blog.

Page 12 of 17 (82 items) «1011121314»