Microsoft Translator Official Team Blog : Live Translator

Politically Incorrect Machines

MSR-MT Team — Sun, 26 Oct 2008 04:57:00 GMT

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

Translate This and Translate My Page Functionality with Windows Live Translator

MSR-MT Team — Fri, 02 Nov 2007 10:26:00 GMT

Every now and then I look at visitor logs on the various personal and professional sites/blogs that I administer. It makes for a fascinating experience to see the many places worldwide that visitors come from. I have often wondered about non English speakers and how I could make my writing more accessible to them. While some professional and company web sites have translated versions available, in many user forums and communities across the web there have been requests for a translated version of the pages/posts. Today, on many sites, I have to copy the text on the site, paste it into a translator and look at the translation. It is cumbersome and not very seamless in an otherwise smooth navigation experience.

I am very pleased to say Windows Live Translator solved this problem with the latest feature addition that rolled out this week. Now on the Live Translator home page you will find a new link "Add the web page Translator to your site". By clicking on this link you go to a page that offers snippets of code that can be added to individual web pages for which you wish to offer translations.

The code generator will create the appropriate widget depending on the source language of your site. Refer to the Live Translator introduction post where Andrea listed the language pairs that we currently support.

So here is what you do to have a link on your web page to translate it:

Step 1: Click on the Add the web page Translator to your site link

Step 2: Select the language your web page is written in (source language)

For example: Since all the articles on my blog are in English, I choose English as the source language

Step 3: The code that you need to copy and paste into your web page's HTML is generated in the box

For example: Since I chose English, the code that is generated looks like this

<script type="text/javascript" src=http://translator.live.com/TranslatePageLink.aspx?pl=en></script>

Step 4: Copy that code and paste it into the page that should offer translation.

For example: On my blog say I want the blog post I wrote about Live Translator to be translated, I go into the blog editor and paste it like so:

If the blog or web page uses templates, one could also paste the code into a template - thereby providing the Translate This Page widget on all pages

Step 5: Enjoy an expanded (and hopefully more appreciative) audience!

The end result on my blog looks like this in the case of a single post translation:

The end result looks like this if I put it in the template (this allows for translation of every post):

For the more technically minded here is some more information on the parameters that the Live Translator accepts:

http://www.windowslivetranslator.com/BV.aspx?lp=en_fr&a=http://viks.org

where lp is the language pair (such as en_fr for english to french) for source and target languages. a is the URL you want translated.

The Windows Live focused community site ViaWindowsLive is making creative use of the Live Translator to make their site available in multiple languages (look on the left bottom of the page). I would love to check out how you might be utilize this new feature. Feel free to post a link to your site in the comments.

-Vikram

Edit: Updating the parameters link

New Live Search and Translation Results Integration

MSR-MT Team — Tue, 02 Oct 2007 13:00:00 GMT

Have you tried the new Windows Live Search? I have been using it as the default search on all my computers at work and home (10+ of them) and am very impressed by the improvements. While all the great new features are quite excellent, I am very pleased with the quality (relevance) of the search results themselves. The rollout was gradual, and most of you should be seeing the new search by now. If not, both the Live Search blogs have direct links to the various features.

On that note, here is some search related news for you from Andrea, your friendly neighborhood program manager for the Windows Live Translator Beta:

Windows Live Translator Beta is now directly integrated in the newest version of Live Search. What does this mean? When a search result (i.e. web page) has been found in a language which is different than the user’s language, and the Live Translator can translate from the web page’s into the user’s language, the search result is accompanied by a new link: “Translate this page”

(User language = English; web page language of all 4 search results = Spanish; translation offered: from Spanish to English)

A click on this link opens the found web page in Bilingual Viewer mode, allowing the user to see the original web page and its translations with all enhancements described in our previous blog entry.

You may ask: how does Live Search know “my” language? Generally, your system settings provide this information. You can change your language settings either in your browser which will influence the behavior of all language(or “market)-sensitive web sites, or you can define a “Display Language” just for your Live Search experience. Live Search’s “Options” menu allows you to select your preferred language in which the Live Search user interface will be displayed to you.

If you choose to select a display language there, it will henceforth be considered “your” language. Any web page found by Live Search that is in a different language from yours may be shown with a “Translate this page” link, provided that translations from the page language into your (selected) language are available. (Please see our introduction blog entry for a list of translation languages we currently offer).

That was Andrea, giving you the scoop on what to expect with the new search integration.

Many times, I find myself searching for deeper meanings for cryptic error codes that programs often throw up. Some other times I find myself searching for any information that might be gleaned about the latest Tablet PCs. These searches tend to turn up sites in other languages with potentially useful information. The new "translate this" integration into search is now a feature that I cannot live without.

Have fun searching and translating!

- Vikram