Microsoft Translator (and Bing Translator) Official Team Blog

Top Sites Going Global with Translator API

Microsoft Translator — Tue, 18 Oct 2011 16:00:00 GMT

The ability to use language and the capacity to translate between languages is one of the characteristics that define us as humans. Over the last decade, world class researchers - both at our own research labs and around the world have been working on the problem of machine translation, the results of which you are able to enjoy today on Bing and in many other Microsoft products.

Last month at the BUILD conference, Satya Nadella, (President, Server and Tools Business at Microsoft) announced the global, high volume commercial availability of the Translator API. This was a significant milestone for us, as we had seen a tremendous increase in demand from partners who see it adding great value to their customers and wanted the reliability, performance and scale of a Microsoft service. It was an added bonus that we were able to deliver this class of service to our partners at a significantly lower price than alternatives. Over the past few months, the diversity and volume of partners using our API has increased rapidly and continues to grow.

A few weeks ago, Facebook rolled out translations powered by our service to many of their major markets across the world. With a user base larger than most countries of the world (barring India and China), and with 75% of the users from outside the US – Facebook is a great example of how the translation API can help partners break down language barriers.

Facebook joins many other partners including Trip Advisor, Harper Collins, Elsevier, Webster and eBay who are utilizing the translation API in innovative new ways to bring their services and content to new audiences and new languages. We hope to showcase many of these in the coming months on the Translator blog.

Today at Web 2.0, in a session titled “The Future of Big Data & the Global Web” we will be outlining the value that this data driven service provides to businesses as they look to expand their business and audience globally. We will also provide an inside look at how the service is built, and showcase some of the partners that have utilized the Translator service to great effect.

The Translator API offers instant text translation, language detection functionality, text-to-speech in multiple languages and innovative collaborative translation functionality. It was designed from ground up for partner use, and thus provides a choice of API interfaces: SOAP, AJAX, HTTP or OData, allowing developers to choose what works best for their scenario. If you are a web site owner looking for a simpler, no-code solution – the free webpage translation widget might be the best choice. It utilizes the same APIs, and provides additional community focused tools to customize the translations to your site and content in partnership with your visitors. A comprehensive FAQ is available here.

We believe in the idea of “Translation being a utility, and not a destination”, and you can join us in supporting that notion by utilizing the API to break down language walls on the web today. Subscribe to the free tier of service to get started. You can always upgrade to a higher level of service if you need to.

Vikram Dendi,
Director of Product Management,
Microsoft/Bing Translator

Also posted to the Bing Search blog.

Microsoft Translator API now supports OData, pricing details for higher volumes announced

Microsoft Translator — Wed, 14 Sep 2011 16:45:00 GMT

Microsoft President Satya Nadella announced major new milestones for the Translator API at his BUILD conference keynote today. We would like to provide some additional detail about the announcement here.

The headlines:

Microsoft Translator API available via the Windows Azure Marketplace at various volume levels to meet your needs

Reiterating our support for standards by supporting OData and adding standards based (OAuth) authentication for greater security

Publishing the pricing model for the various subscription tiers to best fit your needs (in addition to the free tier that we currently offer)

Starting today developers can directly sign up for the Microsoft Translator service on the Windows Azure Marketplace at the level of volume they expect to use. Windows Azure Marketplace is the one stop shop for cloud data, apps and services and we are pleased to utilize this platform to deliver the Translator API to developers. Provisioning the Microsoft Translator API through the Marketplace allows us to deliver the service at higher volumes than we previously could offer, along with the facility to upgrade to higher volume on demand. Additionally, the Marketplace provides a world-class ecommerce back-end which enables us to better serve our global Translator partners and grow with demand.

We are also pleased to announce the addition of OData to our already diverse set of interfaces (SOAP, HTTP & AJAX) to the Microsoft Translator service. Once you subscribe to the offer on Azure Marketplace, you can explore the Odata end point by using the Service Explorer. Starting now, developers are also able to use standards based two-leg authentication (OAuth) to secure calls to API (irrespective of the end point they are using). The full details are available in our developer documentation.

In response to the tremendous demand from existing as well as new partners that wish to utilize a reliable, consistently available, and developer friendly service, we are also pleased to announce pricing for higher volume usage today. In addition to a no-cost tier that is designed for low-volume and hobbyist use, you can today subscribe to higher volume tiers at an attractive price point. You can subscribe to tiers ranging from 4M (million) characters a month onwards, priced at US $10 per million characters. As an introductory offer, we are also announcing a 120 day (4 month) promotional free trial on all paid subscriptions for a limited time. We hope this would allow you to use the service and determine the volume level you would need for your scenario. Existing licensees and users of our API are not affected by this announcement and will have plenty of notice to prepare for the eventual transition onto the unified Marketplace based platform. Please refer to the frequently asked questions (FAQ) page for more details.

Nearly five years ago, we first said “hello world” on this blog. Since then, thanks to an ever increasing user base and enthusiastic developer and business partners we have come a long way. As a team of researchers and engineers at Microsoft Research, we continue to strive to deliver value to Microsoft partners and users worldwide by combining research investments with product development. In addition to our the API, we also provide translation experiences through Bing Translator – our consumer focused webpage and text translation site, through Office, Bing Bar, Internet Explorer and much more. Please don’t hesitate to send us your feedback, comments and questions. We have vibrant user and developer communities where you can discuss the service or ask for help. For questions that aren’t answered in the FAQ or the community, you can also email us at mtcont@microsoft.com (for general comments), or at mtlic@microsoft.com (for specific licensing questions). Please direct any press inquires to mtcont@microsoft.com.

We hope to see you soon from the other side of a translation request!

Vikram Dendi
Director of Product Management
Microsoft Translator

Updated (9/22): Clarification added to title that the free tier of service is not going away.

Announcement: New Microsoft Translator release delivers community tools to customize translations and API enhancements

Microsoft Translator — Mon, 06 Jun 2011 13:00:00 GMT

I am pleased to announce the release of the latest version of Microsoft Translator, with a focus on user features and user experience. This release brings some major new features, and a slew of improvements based on feedback from you – our users and partners.Here are some of the highlights of this release:

Microsoft Translator Widget:

Manage Translators: The popular Microsoft Translator widget, which has been used by thousands of websites to instantly deliver translated pages to their visitors, is receiving a major update. The collaborative translations feature that we released as a technology preview last year is now complete, and adds a user and role management system that enables site owners to collaborate with their visitors, trusted translators and moderators to tailor the translations to their content. The sometimes less than perfect quality of the Machine Translation system is no longer preventing you from delivering your site in high quality to a worldwide audience!

Manage Translations: Now that you can invite experts, your friends or your users to help tailor the translations for your site, how do you manage all these edits that are flowing in? How to make sure you can weed out edits that might not really be relevant for your content? What about languages that you don’t know? Delivered in this release is also a dashboard to moderate and approve translation edits in bulk. The site owner and the invited users can utilize the dashboard to approve, moderate or hide alternative translations in bulk.

See sentences with pending suggestions: In addition to using the bulk editing feature, you can also simply browser the pages and see which translations have pending suggestions. The widget will highlight for you what you need to look at and approve or reject. A blue highlight is for the translation suggestions, a red highlight is for the pending rejections.

Fresh new design: A fresh new design for the Collaborative Translation functionality. Based on feedback from beta users, and taking into account usability considerations we refreshed and streamlined the user experience of showing/editing alternative translations. This should make it easier for users to immediately get some information about how the community is using the alternatives, select their favorite alternative or provide a new alternative.

Microsoft Translator API:

I wanted also to reiterate that our API is not going away, and we continue to be focused on adding value to our partners through continued improvements. In this release we have made several improvements based on your feedback. We are very pleased to see the many applications and scenarios that are being built using the API, and we hope to showcase more of them on this blog. If you would like your application showcased, contact us at mtcont@microsoft.com. If you would like to use the API for production purposes, just send an email to mtlic@microsoft.com to receive the free use commercial license agreement. As you can imagine, we are seeing a significant increase in these requests so we greatly appreciate your patience in waiting for a response.

Full access to the edits from your community: We promised to give you access to the alternative translations that have been generated as you worked with your community to tailor the translations to your site or scenario. We are pleased to add this functionality to the Microsoft Translator API. It is beta, so please be gentle.

More flexibility around API traffic limits: We are removing the fixed limit on the number of requests per minute that you could push to the service. We are replacing it with a more flexible mechanism that we will outline in an upcoming blog post.

There you have it. Some of the awesome new features in this release. For those of you who have been patiently waiting for invitations to try out the collaborative features of the widget, you should start seeing these invitations arrive in batches starting now.

Stay tuned for more detailed information on each of these features and more!

Vikram Dendi
Group Product Manager
Microsoft Translator

Showcasing some great consumer applications powered by Microsoft Translator API

Microsoft Translator — Tue, 01 Feb 2011 10:23:00 GMT

While we are quite proud of the applications and services that we have built, we are even prouder of the many wonderful applications built by our partners using our extensive set of APIs. In this series, we wish to highlight some of these apps.

Polyglot – an elegant Windows Phone translator application

You might have used the free Translator app on the Windows Phone marketplace, but you should definitely give Polyglot from Very Software a try. With a beautiful interface that works in either orientation and delivering translations on the go – Polyglot is undoubtedly one of the best looking Windows Phone applications in the market.

Home Page

Kywix Babilia HD – a highly functional application for iPad which offers translation and more

One of the fast growing applications that is well optimized for the larger touchscreen. Integrates with Dropbox for source material, and with Facebook and Twitter for quick sharing of translated content. Check out the various elegant touches – including the capability to translate PDF, learn new vocabulary and tv-out support.

Home page

There are many other free and paid applications built using Microsoft Translator APIs - we would love to hear of any others you would like showcased here.

Indonesian, Ukrainian and Vietnamese are now available!

Microsoft Translator — Sun, 10 Oct 2010 02:27:43 GMT

What do Ukrainian, Vietnamese and Indonesian have in common? They all have very passionate communities that have for a while been encouraging our team to add support for these languages. A glance at the comments on this blog, and on our forums show the enthusiasm with which users have pursued adding these languages, and that has spurred our team on to work hard towards this goal.

We are proud to announce that with our latest release, we added these three languages to bring our total number languages to 35. The Microsoft Translator machine translation system can now deliver translations in the following languages:

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

This means that you can use the Bing Translator text and web page translation functionality in all these languages.

You can also translate text and documents between these languages from within Office. To see these languages in your Office translation language list, you would need to have the LIP (Language Interface Pack) for that language installed. More details here.

Personally, I am quite excited at being able to follow what my friends are saying in these languages on Facebook and Twitter (by using the visual preview of the Internet Explorer accelerator)!

Finally, you can also deliver your web pages to your site users using the Microsoft Translator widget. Not only that, with the collaborative translations feature you can tailor the translations to best suit your content. You can try it on this blog right now – translate to a different language, hover to see the popup that shows the original sentence and click “More Translations” to edit/select the translation to be delivered.

We continually work on improving all our languages, so if you notice the engine not providing the best translation today – you might want to try again in a few weeks to see if it’s improved. For those of you using the API or the widget to translate content in your applications or on the web, you can always use the collaborative translations functionality to make edits to the machine generated translations today (so you don’t have to wait).

Once again, if you are part of our one of these three communities – congratulations on working with us to “ship” these new languages! We will continue working towards adding more languages in upcoming releases.

We will look forward to hearing from you (please email us at mtcont@microsoft.com). You can also interact with the community on our forums.

Say hello to performance & security

Microsoft Translator — Mon, 20 Sep 2010 20:03:00 GMT

Over the last few months, while our data and languages specialists have been continuing their focus on improving language coverage and quality, the rest of the team doubled down on performance, infrastructure and bug fixing. After the big release at MIX we took the next release as an opportunity to focus on ensuring a strong foundation which can support the rapidly increasing demand for the service and fix any fit and finish issues that were postponed in the run up to that release.

A data center move, several significant user experience related performance improvements, a more scalable service infrastructure and a bunch of bug fixing later here we are with product offerings that are more performant than ever before. You may not be able to notice all the improvements, but a sampling:

Webpage Translator (Bilingual Viewer): The most visible change is the default “view” – the “translation-with-hover-original” is now the view you are presented with if you are a first time visitor. This is a change that is geared towards the most common usage scenario of the bilingual viewer where our users are looking to seamlessly translate and browse various web pages. The side-by-side view is still available just a click away, and we remember your preference of view once you switch from the default. We certainly have quite a few users who love the side-by-side view especially when using wider screens or learning a new language. You can learn more about the bilingual viewer in this blog post. Along with this change, we have been able to improve the load time, the translation time and reliability of translations on long pages. There was also a significant speed increase in English to Chinese (simplified) translation performance. Try it now!

Office: Those of you using the translation functionality in Office will also benefit from the performance related improvements. For those that haven’t tried it yet, you can right click on a selection within Office products and select “Translate” to have the text be translated instantly. In Office 2010, you should be able to do this without any configuration. You can check out the manual setup instructions for Office 2003 and Office 2007 in case you are unable to see Microsoft Translator powered translations in your Office install.

SSL (HTTPS) support: You are now able to securely send text to the translation service when using the API. We have also enabled the Widget to work seamlessly on SSL protected pages (without any security warnings). This has been a frequently requested feature from many of our users and we are glad to bring it to you in this release. Those of you who already generated widget snippets for your sites, should be able to get the HTTPS enabled widget by regenerating the snippet from the widget adoption portal. On the topic of the widget, the widget again works with Norwegian now.

Text to Speech: We have added Asian language support to our Text to Speech API and user focused features. You can now “Translate-and-Speak” in Korean, Japanese and Chinese! To try it, translate something to any of the languages that we support TTS in (Chinese , Korean and Japanese in addition to English, German, Spanish, French, Italian, Portuguese, Russian) and you should see a speaker icon above the translation.

We took the all the great feedback that our users gave on the Collaborative Translations functionality (thank you for that!) and have made a number of improvements in both the user experience and how we handle input. Finally, many of you noticed that the dictionary functionality was turned off for a little while – now it is back!

We hope you enjoy all the improvements and new additions. Post your feedback or questions on our developer and user forums.

Collaborative Translations: Announcing the next version of Microsoft Translator technology – V2 APIs and widget

Microsoft Translator — Mon, 15 Mar 2010 12:00:00 GMT

There have been many stories about brain vs. brawn. More recently, human brain and computer brawn have been pitted against each other in arenas such as one-on-one chess. We all have been hearing about applying large amounts of computing power to solve problems like translation by sheer force. As a high performance cloud service offered by Microsoft, we continue to make investments in such processing power – but we also know that no matter how many machines you throw at translation, it is still impossible to get the correct, error-free, contextually accurate translation every time. With the clear understanding of how it would be a much better outcome for our users and partners, we have been hard at work exploring ways of putting together the might of the machines and the power of human understanding. The first wave of innovations focused on our partners and users was what we called “Anywhere Translations”.

Welcome to the next wave of innovation – Collaborative Translations.

Microsoft is pleased to announce, the availability of the Collaborative Translations Framework – a technology that combines the scale and speed of automatic machine translation with the accuracy and context awareness of human translation. At MIX 2010, we are announcing the latest version of our translation API (v2) and built on top of that, a new version of the pioneering translator widget that we released a year ago. In addition to bringing real-time, in-place translations to your web site, the Microsoft Translator web page widget v2 adds collaborative features that help tailor the translations delivered to fit your site.

In addition to the collaborative features powered by the Collaborative Translations Framework, the V2 of the Microsoft Translator API includes a “batch” interface to translate large amounts of data, support for communicating with the service securely via SSL and the addition of “Translate-and-Speak” – a text-to-speech functionality. We are also adding an enhancement to our Bing Translator user site, where you can use the “Translate-and-Speak” functionality whenever you translate into one of the supported languages.

What is being announced today:

1) A simple to adopt, highly customizable widget that site owners and webmasters can place on any webpage – and it not only helps to instantly make the page available in multiple languages, it also allows the owners with the help of their community or professional translators to tailor the the translations to their site’s content.

2) A broad set of powerful translation APIs in SOAP, HTTP and AJAX flavors so that developers can pick the best one to fit their requirement. Functionality includes language detection, single and batch translation, collaborative translations and text to speech. All you need to get started is a Bing Developer AppID. In addition, we are also announcing the Microsoft Translator Silverlight control for translation will be available as part of the Silverlight toolkit.

3) An update to Bing Translator translation service, which adds the “Translate-and-Speak” functionality for a set of languages (English, German, Spanish, French, Italian, Portuguese, Russian). Perform a translation on the site and you will notice a speaker icon to click on to hear it spoken.

Who is it for:

The Widget is for anyone with a web page. If you can paste a small snippet of code into your page, you will be able to display the widget to your audience. No need to know programming intricacies, or how to call a JavaScript API. No need to write or install server side plug-ins for your specific software.

The APIs are for anyone that would like to bring translations to their app or site. Some developers have used the APIs to deliver applications that can deal with content in multiple languages, and others have used them to localize their applications. Designers have used them to make sure their designs work in many locales, and enterprises have used them to translate documents. Phone application developers might find the cloud text-to-speech API particularly interesting, as they develop hands-free scenarios.

What is cool about it:

Innovative: The translator widget pioneered the in-place instant translations (without taking users away from the site) and now it delivers the tools for sites to customize how the content gets translated. Users can edit/select or report the automatic translations to better fit the content and site owners have final say in picking the best translation for their content. Users in a community help other users and the community owner, and one community helps another community as sentences repeat. The APIs enable any developer to take advantage of the power of collaboration, and can tap into the wisdom of their crowd(s) across multiple scenarios.
Easy to Use: Adding the widget to a page is as easy as copy and paste. Using it on the site is as easy as select language and click the button (and in V2 we provide the option to make it automatic!). The APIs are simple and straight forward. The choice of SOAP, HTTP and AJAX allows developers to pick the one most familiar or easy to use for their application.
Customizable: From color and size selection to the translation behavior – everything about the widget is customizable to fit the site’s requirements.
Thoughtful User Experience: Progressive rendering allows for the page to get translated progressively – without having the user stare at a white space while the translation is being performed. The translation toolbar that appears when the translation is kicked off provides a progress indicator, the languages selected and a way to turn off the translation. Auto and Notify preferences and an option to hide the widget control help deliver the optimal user experience to the visitor of a site.
Localized: The entire widget experience, including the alternatives UI are all localized to multiple languages. Users visiting a site with their browser set to a different language will see the UI in their language.

Fun! What does it cost:

The widget is completely free for use on commercial or non-commercial sites. Instead of expensive localization whose costs are incremental if a site has changing content, the translator widget brings a no-cost option to site owners. Depending on their needs, site owners can choose to invite their chosen translators to come help improve the translations delivered to their site.

The APIs are also available at no cost to developers and partners. For high volume commercial use, email mtlic@microsoft.com.

How do I get it:

Each MIX 2010 attendee gets an exclusive invite code in their attendee bags to enable Collaborative Translations features in their widget. If you are not attending MIX, you can still get a widget for your site, and add yourself to the Collaborative Translations feature invite list. We will be sending invites as soon as some more become available.

What we are working on:

More polish:We will be looking for your feedback and continue to work on the fit and finish for the widget, toolbar and alternatives UI. We are also working on providing better translator invitation management as well as analytics for site and app owners. We would love to hear your feedback about the “translate-and-speak” functionality.
More customizability: We will be evolving the customization options available to you through the adoption portal. We will also be looking at your feedback on the overall design of the APIs and the functionality available through the GetTranslations & AddTranslation methods. We are working on providing language selection options (so site owners can limit the number of languages they show as part of the widget). We are also working on adding export functionality for your site’s edits.
Compatibility: We are working hard to ensure that our user interfaces are broadly compatible with most modern browsers (widget and translate-and-speak) and sites (widget and Bing Translator). Make sure to check back often if a feature did not work in your browser – we update often.
Silverlight: We are working on making the Silverlight translator control available as part of the Silverlight toolkit release that would be shipped when SL4 goes final.

Other questions:

I can’t get it to work or I have encountered a bug. Where can I get support or provide feedback?

Given the pre-release nature of the new functionality you might encounter glitches as we work towards adding new features. The known issues list is available here. If there is an issue that you encounter which is not in the list, we would love it if you could let us know. You can either use our forums, or directly contact us at mtcont@microsoft.com.

Can this save me the cost of doing expert localization of my professional website?

Expert localization is an extremely important and valuable aspect of doing business globally. We have always encouraged our users to take advantage of the exceptional quality of translations provided by an expert translator for mission critical content that needs to be localized. For those of you who are looking for a low cost way to localize content that you might not otherwise have localized, or for content that is rapidly changing (and not cost effective to use expert localization) – our machine and human collaborative translations option could come in handy and save money.

How many languages do you support? When can you add support for <insert language here>?

We continually work on adding new languages – since last MIX we added 17 new languages bringing us to 30. Here is the list of languages we currently support:

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

You can always find the latest list of languages here.

I am using a hosted service for my site/blog that does not let me use javascript widgets. What can I do?

We are looking to work with providers of hosted services to make adding the widget an easy process for their users. If your provider does not offer this, please let them and us know that you would like to see the widget work with your site.

Those of you who are at MIX 2010 can dive deeper into these technologies at our session (Monday 3/15, Lagoon H at 2:00 PM). We will also be posting in-depth information about the various aspects of today’s announcement in the next few days. Keep checking this post and our forums for further announcements, known issues and more information. You can follow our MIX10 coverage on twitter.

MIX MIX MIX… and some late night goodies

Microsoft Translator — Sat, 13 Mar 2010 07:43:00 GMT

It’s nearly midnight in Seattle. The team is heads down in preparing the service for MIX 2010… I am sitting in the office wondering which of my 100 to-do items I should tackle next. So, naturally, I do something that’s not on that list. Something fun. :)

As I mentioned in my earlier post, MIX is our favorite conference and so we put “money where our mouth is” (let’s see a machine translation system deal with that one!) and said an enthusiastic yes when the team asked us to be a sponsor. All you lucky MIX attendees will see some awesome swag in your bags courtesy Microsoft Translator, with one of the highlights being a lovely decal for your notebook/pad/device.

Everyone liked the design we came up with for it so much that we decided to make a wallpaper out of it for you. So, without further ado:


Dark: 1920x1080 /1440x900	Light: 1920x1080 / 1440x900

Once again, don’t forget to come to our session on Monday at 2 PM at Lagoon H and also visit our Showcase demo area at The Commons.

Enjoy!

- Vikram Dendi, Senior Product Manager, Microsoft Translator

“Anywhere” Translations

Microsoft Translator — Thu, 11 Mar 2010 09:20:00 GMT

Nearly a year ago Microsoft Translator unveiled an innovative new approach to translating web pages – one that enabled webmasters to bring the power of automatic machine translation to their sites with a snippet of java script. Unlike any other quick and easy solution out there at that time, the Microsoft Translator webpage widget integrated the translation experience into your site, and did not take your users away to a different translation site. Here is our friend Doug Thomas, in his inimitable style, explaining how the same powerful translation technology that powers translation inside Office can power your site.

The widget was a showcase for the broad set of APIs that we announced at the same time – APIs that have been used by many partners since that time to build a variety of software, services and sites.

You all know that we were the first major translation service to provide a Haitian Creole system to help with the relief efforts underway in Haiti. One of the key motivators for us to build the system was Rick Engle, a fellow Microsoft professional who in his various endeavors to help with the relief efforts wanted to write an application to help the workers on the ground in Haiti. Since the time we added the language to our supported list, Rick went ahead and built the mobile app he had originally set out to build. You can find it here and it works for all languages that our service supports. The goal for having a full set of APIs (including HTTP, SOAP and AJAX) has always been to help developers like Rick focus on building great applications without a lot of heavy lifting, and we will continue to invest in that direction.

When we announced the availability of the widget and the APIs, we articulated our mission – to empower content providers, site owners and developers to deeply integrate translations into their sites and communities – truly bringing translations “anywhere” they are needed. As MIX 2010 approaches, we are working towards showcasing the next wave of our partner focused innovations.

We love MIX – where we get to meet developers that understand design, designers that understand strategy, strategists that understand technology... We get to discuss language technology with a German developer building software for an English company that serves customers from China to Brazil and we get to hear great feedback about what new browsers should we be testing our AJAX controls against. It’s a brilliant “mix” of creativity, ingenuity and passion and we are glad that we have made it “our” conference to share with the world what new things that we have been cooking up.

A bunch of us with be at MIX2010, and those of you that will be there can expect some goodies in the attendee bag from our team. Do mark your schedule for our session – it’s at Lagoon H on Monday at 2 PM. If you were at last year’s session – you know how much fun it is. Oh also - we have some heavy boxes we are lugging with us. :)

If you are not at MIX (this is going to be the most attended MIX ever!), do not worry. We will have plenty of information posted here and on our site about what we are announcing at MIX on Monday. In addition, we hope to have Doug back – explaining the latest and the greatest in translation soon after that. Stay tuned!

- Vikram Dendi, Senior Product Manager, Microsoft Translator

Announcement: New languages added to Microsoft Translator (and Bing Translator)

Microsoft Translator — Mon, 01 Mar 2010 10:57:10 GMT

A little while ago I was asked to figure out a solution to a user experience problem that was affecting some of our offerings such as the widget, the Bing text and web page translators. A “bug” was assigned to me, asking me to weigh in on how to deal with a problem of plenty: Given we were about to add a substantial set of new languages we were running out of space to display them properly. What could be a quick interim fix?

Several months ago, while announcing the availability of Hebrew in our language list, I had requested our community of users what else they wanted to see supported. Taking into account all the feedback that came in since then, we have been hard at work to add support to new languages. This is why it’s always a pleasure to encounter problems like the one above – they indicate that this work was coming to fruition.

I am happy to announce the addition of seven new languages to our translation service. As always, they will be immediately available for your use through the APIs and all the products that consume the service. Here is the list of languages that have been added in the latest release. In addition there have been several updates to the Haitian Creole language since we last talked about it here.

New languages:

ROM - Romanian
NOR - Norwegian
HUN - Hungarian
SKY - Slovak
SLO - Slovenian
LTH - Lithuanian
TRK – Turkish

This brings our languages supported number to 30 languages. Here is the full list:

Currently available:

ARA - Arabic
CHS - Chinese Simplified
CHT - Chinese Traditional
NLD - Dutch
ENU - English
FRA - French
DEU - German
HEB – Hebrew
HT – Haitian Creole
ITA - Italian
JPN - Japanese
KOR - Korean
PLK - Polish
PTB - Portuguese
RUS - Russian
ESN - Spanish
CSY - Czech
DAN - Danish
ELL - Greek
SVE - Swedish
THA - Thai
BGR - Bulgarian
FIN – Finnish
ROM - Romanian
NOR - Norwegian
HUN - Hungarian
SKY - Slovak
SLO - Slovenian
LTH - Lithuanian
TRK - Turkish

Head on over to our forums if you have specific feedback or looking for discussions about these new languages. We continue to work on adding even more languages to the service, so please keep sending us feedback and stay tuned for other announcements on this blog.

With the addition of these new languages, the approach I recommended in the short term is visible in the translation toolbar – the language list uses a smaller font size. In the future, we intend to move to either a multiple column list, or another style of display for the list.

I will look forward to more such problems, since it means we are meeting more expectations from you - our users. Enjoy the new languages!

- Vikram Dendi, Senior Product Manager, Microsoft Translator

Have you tried to translate that site today?

Microsoft Translator — Fri, 26 Feb 2010 08:55:00 GMT

Translating a website can be tricky – especially if it is not one that you built. A year back at MIX, we helped webmasters and developers take a step towards delivering a seamless, well integrated translation experience using the translator widget and the APIs. Yet, there are still many sites out there that users still need to translate without the help of such technology. Thus the continued popularity of our webpage translator, and the bi-lingual viewer feature that it pioneered.

While our webpage translator translates millions of pages every day, we keep an eye on pages that are problematic to translate and we look closely at user feedback. Our goal is to not just deliver a translated page, but also try to stay close to the fidelity and layout of the original. As web pages grow richer, adding layers of interactivity through increasingly complex javascript – they become more difficult for traditional proxy based translation services to handle.

Some of you might have noticed a significant improvement in how the webpage translator handles certain web pages that it had not done so well in the past. A couple of weeks ago, we released an updated version of the webpage translator that improves site compatibility and delivers better performance. If you have not tried it recently, we urge you to try any sites that you had not been able to get webpage translators to translate on this new release. As always, if you do find problems please don’t hesitate to contact us.

Speaking of MIX, keep an eye on MIX 2010 this year. In addition to the all the buzz around Windows Phone, don’t miss out on this session. :-)

Updating the Haitian Creole Translation system

Microsoft Translator — Sat, 30 Jan 2010 22:27:56 GMT

Most of you know that we released the first publicly available Haitian Creole statistical machine translation engine last week and have been hard at work making it even better. I am pleased to announce since last night we rolled out two updates to the system and our site which bring several improvements:

1) More training data = better translations. We trained the system on even more training data (including data that we hand translated) which should reflect in better translations. We are nowhere near done yet, and we will continue to work on this.

2) Updating the AJAX API and widget. The Translator widget (and the underlying AJAX API) now accurately reflect “Haitian Creole” as the language selected in their UI. This was primarily a user interface fix (the Haitian Creole translation itself worked fine). You can use the widget to deliver any webpage in any of the languages we support (including Haitian Creole).

3) Please don’t forget the broad set of APIs and webmaster resources that are available for those that are building applications and websites to help with the relief efforts. There are several efforts underway to develop mobile apps (using the SOAP or HTTP API) and websites (using the AJAX API). If you are working on something along those lines, leave a link to your app/site in the comments and I will make sure to surface them up here so people can find them more easily.

We will continue to work on improving the system and we wish to thank everyone in the community that has been instrumental in helping us get this much requested translation engine out of the door. Stay tuned for more announcements!

Also, let me once again point to a resource where you can help with the broader Haiti relief efforts. Please help in any way you can!

Update (1/31): The DIPLOMAT project at CMU in the 1990s was an earlier project to create a Haitian Creole system for DOD/DARPA. As I mentioned in our earlier blog post, our system makes use of CMU’s data from that project.

- Vikram Dendi, Senior Product Manager, Microsoft Translator

Announcement: Haitian Creole support in Bing Translator and other Microsoft Translator powered services

Microsoft Translator — Sun, 24 Jan 2010 19:15:11 GMT

In the current crisis in Haiti there are a number of initiatives to rapidly build software to assist in humanitarian aid. Responding to community requests for a machine translation (MT) system to translate between English and Haitian Creole, our team has been hard at work over the last few days. I am glad to announce that an experimental Haitian Creole MT system is now publicly available via several services and APIs powered by Microsoft Translator technologies. We will continue working on improving the system, but we hope meanwhile that in spite of the experimental nature – it will be of use in the relief efforts.

1) What is being announced today?

Responding to requests from the community involved in Haitian relief efforts, Microsoft Research is making available today an experimental machine translation system for translating to and from Haitian Creole. You can try it at http://translate.bing.com or http://www.microsofttranslator.com.

2) How is it significant?

With the devastating disaster that struck Haiti, we have all been individually pitching in to help the efforts. This is our effort, as a team, to respond to the needs of communities such as Crisis Commons by delivering a Haitian Creole translator which can be of help to individual users, as well as other technology projects that could use a scalable translation system in their relief endeavors. Further, the usage of our API is completely free and it can be built into any application or website for immediate use. We hope that this might help the many applications being developed (such as those on crisiscommons.org) to aid the humanitarian efforts.

3) How can I use this system?

The Haitian Creole translator is now part of the Microsoft Translator web service enabling many of the user scenarios powered by the service. Users can access the service through the Microsoft Translator web site. Developers would be interested in looking at our APIs – and choose from SOAP or HTTP (Support for Haitian in our AJAX API will be rolled out in the coming days).

4) How is it different from other efforts?

There have been some great efforts in quickly building dictionary and rule-based Haitian Creole translation tools. The statistical machine translation system behind Microsoft Translator allows for a continuous improvement in the quality of translations (by adding more training data). Also, by delivering this as part of our web service we can ensure scale and performance and open up the possibility of using our many scenarios (Bing Translator, Internet Explorer 8, Messenger Bot etc.) with Haitian Creole, as well as using our extensive API set to add such support to other software and web sites at no cost.

5) What was involved in getting this out of the door in record time?

The process involved identifying parallel (translated) data between English and Haitian Creole, and training the MT engine to create the requisite language models. We would also like to acknowledge the great work being done the Crisis Commons folks, the dictionary builders at haitisurf.com, the folks at CMU that made available parallel data and the Microsoft volunteers who challenged our team to action.

6) What should I expect in terms of quality?

This is an experimental system put together in record time. While our typical approach to adding new languages involves significantly larger amounts of training, a higher threshold for quality testing – we decided that the upside warranted making the system available to the community at the earliest, and continue improving it subsequently. We are working diligently to keep improving the quality, but bear with us if you encounter problems. You can always contact us at mtcont@microsoft.com with feedback. Our user and developer forums are also available to discuss any issues you encounter.

7) How can I help improve the system?

The best way you can help improve the system is by helping us find more training data. This is typically sentences or words translated between English and Haitian Creole. We intend to make available to the larger community (via tausdata.org) data that we collect (as license restrictions permit) for training purposes. If you know of dictionaries, translated sentences, or websites that have such translations we urge you to contribute it to TDA’s TAUS data sharing initiative. TDA is a non-profit organization providing a neutral and secure platform for sharing language data. If you have any concerns or questions feel free to contact us at mtcont@microsoft.com.

8) How can I help the broader Haiti relief efforts?

Go here to learn more about how you can help those devastated by the earthquake.

9) Where can I get more information?

Please stay tuned to our blog for further announcements. You can learn more about Microsoft Translator and the services we offer here.

10) What can we expect next?

In the coming days expect to see support for Haitian Creole added to even more of our scenarios (Translation Bot, Translator widget, Office etc) as well as the AJAX API. Known issues and announcements can also be found on our forums.

We hope that this contribution proves useful to the various humanitarian efforts underway, and please stay tuned to this blog for further news on the Haitian Creole language support. If you have any questions feel free to contact us at mtcont@microsoft.com.

Update (2:53 PM PST): The Messenger Translation Bot can now speak Haitian Creole. Add mtbot@hotmail.com to your messenger buddy list. Try the group conversation feature with a Kreyol speaker!

-Vikram Dendi, Senior Product Manager, Microsoft Translator

TechEd Europe: Microsoft Translator widget and APIs in beta

Microsoft Translator — Tue, 10 Nov 2009 16:37:20 GMT

Hallo aus Berlin!

Thanks to the great feedback from the early adopters of the Microsoft Translator widget and APIs, we are pleased to remove the invite requirement and move the widget and APIs to public beta. Anyone can now generate a snippet for their site or application from the widget and AJAX API adoption portals.

Likewise, we are also pleased to announce the availability of API (SOAP and HTTP) licensing terms for commercial applications. Feel free to email mtlic@microsoft.com for more information. While in beta, there is no charge for commercial use of the API. The widget and AJAX API continue to be free for commercial use under the standard terms of use.

Thank you for all those who attended today’s session at TechEd Europe. Here is a recap:

Microsoft Translator APIs and the webpage widget are now in beta
Generate a translator widget for your webpage here, or use the AJAX API to further customize the translation experience
Detailed reference for the APIs on MSDN, Getting started guides for ASP.NET and PHP, Interactive SDK
20+ languages supported by the service now (the latest 2 to be added in the next few days – Finnish and Bulgarian)
New to windows 7 and Internet Explorer 8? Try the “Translate with Bing” accelerator powered by Microsoft Translator!
Microsoft Translator powers millions of translations each day for Office (2003-2010), Bing, Live Toolbar and the unique Messenger bot
Commercial licenses for the SOAP and HTTP APIs are available at no cost. Contact mtlic@microsoft.com for more details

We also greatly appreciate all the great feedback on what languages you would like to see, and we hope to satisfy many of the requests within the next few months. Stay tuned and keep the feedback coming!

-Vikram Dendi

Microsoft Translator

Twenty is a nice round number – say ยินดีต้อนรับ (welcome) to our newest release!

Microsoft Translator — Tue, 15 Sep 2009 12:31:05 GMT

In my last update I had asked about what languages you wanted Microsoft Translator service to support. Thank you for taking the time to respond. We are pleased to announce that last week we added Czech (CSY), Danish (DAN), Greek (ELL), Swedish (SVE) and Thai (THA), taking our language count to a nice round 20.

Here is the complete list as of today:

ARA – Arabic
CHS - Chinese Simplified
CHT - Chinese Traditional
NLD - Dutch
ENU - English
FRA - French
DEU - German
HEB - Hebrew
ITA - Italian
JPN - Japanese
KOR - Korean
PLK - Polish
PTB - Portuguese
RUS - Russian
ESN - Spanish
CSY - Czech
DAN - Danish
ELL - Greek
SVE - Swedish
THA - Thai

You will be able to translate between these languages in all Microsoft Translator powered services including Bing Translator, Internet Explorer Accelerator, Office, Widget as well as in our APIs. Feel free to send in your feedback on the new languages via the forum. We do keenly follow your recommendations and requests as we prioritize new languages – so please do keep them coming in the comments section!

-Vikram Dendi

Microsoft Translator

Hebrew support is here. What do you want to see next?

Microsoft Translator — Tue, 07 Jul 2009 11:35:02 GMT

שלום לעולם!

I am pleased to announce that we just added Hebrew to the list of languages that we support. You can immediately use it in Bing Translator, in IE8, with the widget, with the messenger bot, inside Office and of course with the API.

I would like to congratulate our language quality and coverage team on the progress they have been making with new languages. Over the next few months you will see more languages added to the mix, and also continue to see quality improvements for existing languages. Feel free to leave a comment on this thread about any languages you would particularly like to see.

We have also had many of you contacting us about helping find data sources that can be useful to train the machine translation system on – we appreciate your help! Our email address is mtcont@microsoft.com. Do stay in touch!

-Vikram

Microsoft Translator Instant Answers Now On Bing

Microsoft Translator — Thu, 11 Jun 2009 09:46:00 GMT

Use Bing to instantly translate queries from one language to another with our translation Instant Answer! Starting today, when you are looking for a translation of a word or phrase, go to Bing.com and kick off an instant translation, powered by Microsoft Translator. Instant translation is another way that Bing helps you complete tasks faster by presenting better organized and more relevant content.

What to expect?

Example query: translate I love you

Bing returns:

Example query: translate I love you to Japanese

Bing returns:

Example query: how do you say apple juice in Spanish

Bing returns:

Enjoy!!

Cheers,

Lane Rau

Microsoft Translator

Any-to-Any Translations and Language Autodetect now available for Microsoft Translator

Microsoft Translator — Tue, 26 May 2009 10:35:06 GMT

Today our team released some exciting updates for Microsoft Translator! It is now possible to translate from any of our languages to any other language. Spanish to Chinese? Arabic to German? Check :)

We have also added a Language Autodetect feature to our webpage translator. So if you’re on a page that’s in a language you don’t recognize, our translation engine will autodetect the language on the source page, and automatically start translating into the language of your choice.

We’ve also cleaned up our landing page to try and make it a bit easier to use. Let us know what you think!

In addition, some of you noticed that there was a bug for some PC configurations with IE8. There was a bug where the IE8 Accelerator did not remember the user’s selected language. With this release, the bug has been fixed. Thanks to those of you who caught the bug and let us know!! An added bonus: you can also translate from any language to any other language in the preview pane!

Download the Microsoft Translator installer for Microsoft Office

Microsoft Translator — Thu, 16 Apr 2009 21:17:00 GMT

Now you can translate your Microsoft Office documents with Microsoft Translator – right within Office! You can translate words, phrases, or even your entire document, through the Research task pane. We blogged about setting this up manually for Office 2007 or Office 2003 previously - now it's really easy!

This works for both Microsoft Office 2003 and 2007. The current default in Microsoft Office is WorldLingo – this installer will update your task pane to use Microsoft Translator as the default translator for the languages we provide.

Download the installer now and let us know what you think over in the Forum!

Silk Road Power Trio: New API features, Microsoft Translator, PowerToys CodePlex Launch

Microsoft Translator — Tue, 24 Mar 2009 23:58:00 GMT

Our friends over in Live Search featured Microsoft Translator in their MIX09 blog post - check it out!

Announcing the Microsoft Translator web page widget

Microsoft Translator — Thu, 19 Mar 2009 02:04:00 GMT

The Microsoft Translator team is very proud to announce the technology preview of an innovative offering for web page translations. Attendees to MIX09 this week get a special invitation to try out the Microsoft Translator web page widget. We are also accepting registrations, and will be sending out more invites as they become available.

What it is: Built on top of the Microsoft Translator AJAX API (also announced today) it is a small, customizable widget that you can place on your web page – and it helps you instantly makes the page available in multiple languages.

Who it is for: Anyone with a web page. If you can paste a small snippet of code into your page, you will be able to display the widget to your audience. No need to know programming intricacies, or how to call a javascript API. No need to write or install server side plug-ins for your specific software.

What it offers: It provides a simple interface to anyone that visits the web page to select and translate content into a different language. You can see a demo on this page.

What is cool about it:

Innovative: Unlike other (including our) existing solutions, it does not take the users away from the site. The translations are in-place and instant. Users can hover over the translation to see the original.
Easy to Use: Adding it to your page is as easy as copy and paste. Using it on the site is as easy as select language and click the button.
Customizable: You can pick the colors that best blend into your site design. You can pick the size that would best fit into your design (in fact the widget has an adaptive layout that better uses real estate when very wide).
Thoughtful User Experience: Progressive rendering allows for the page to get translated progressively – without having the user stare at a white space while the translation is being performed. The translation toolbar that appears when the translation is kicked off provides a progress indicator, the languages selected and a way to turn off the translation.
Localized: The UI is available in multiple languages – so users that come to your page with their browser set to a different language will see the widget in their language.

Fun! What does it cost: It is completely free. You can put it on any site – commercial or non-commercial. You are only limited by the invite codes available at this point, but over the coming months we plan to make it more widely available.

What we are working on:

More polish: We will be looking for your feedback and continue to work on the fit and finish for the widget & toolbar UI.
More customizability: We will be evolving the default color palette available to you through the adoption portal. We will also be looking at your feedback on the overall design.
New Features: There are a bunch of very cool features that we are working on that will be added soon (your widgets will inherit most of these features). These include “Automatic” translations on page load, multiple layouts/views (bringing in the well received views feature of our bi-lingual viewer offering) and some surprises that we are working on with other teams at Microsoft.

Other questions:

I can’t get it to work. Where can I get support or provide feedback?

I would like to highlight that this is a technology preview release – so please do test it on your site before presenting to your users. The Microsoft Translator forums are now live. Feel free to head over and interact with other users. You will also find members of our team there who can help.

Can this save me the cost of doing human translation on my professional website?

Our goal (and that of most machine translation systems available today) is to provide what we call “useful” translations. While the technology is improving month to month, it will still take a long time before it can match human translation quality. We don’t recommend using machine translation for sensitive or highly critical information. You can learn more about translation quality here and here. You can learn more about how we do machine translation here.

How many languages do you support? When can you add support for <insert language here>?

Currently we support the following languages.

· Arabic

· Chinese (Simplified & Traditional)

· Dutch

· French

· German

· Italian

· Japanese

· Korean

· Polish

· Portuguese

· Russian

· Spanish

Polish was our most recent addition. Our goal is to keep adding languages as we get enough training data to meet our minimum (“useful”) quality criteria which include both standard measurements and human evaluations.

I am using a hosted service for my site/blog that does not let me use javascript widgets. What can I do?

Keep checking this post and our forums for announcements, known issues and more information. You can follow our MIX09 coverage on twitter and on Vikram’s blog.

Last Updated: 3/18/2009, 4:15 PM

Announcements and Sessions at MIX09(Updated)

Microsoft Translator — Wed, 18 Mar 2009 22:50:00 GMT

The Microsoft Translator team is sponsoring MIX 09 this year and we will be showing off the new web page translation widget and the translator APIs. If you are attending MIX, come to our session!

All attendees go widget invite codes in the bags. At this session you will see how you can make use of them.

MIX09-B05M Exposing Web Content to a Global Audience Using Machine Translation. San Polo 3401 | Thursday March 19 |1:25 PM-1:45 PM

We will also be at the Live Search session.

MIX09-T33F Customized Live Search for Web and Client Applications. Delfino 4001| Thursday March 19 |1:00 PM-2:15 PM |

We will also be giving out the exclusive API invite codes at these sessions – so make sure to be there!

Keep an eye on this blog for further news and tidbits from MIX.

- Vikram Dendi
Business Strategy & Front End Program Management
Microsoft Translator

Polish now available on MicrosoftTranslator.com

Microsoft Translator — Fri, 23 Jan 2009 19:48:09 GMT

We are happy to announce the release of our English <-> Polish translation engine! Some of you have been asking us about Polish translation, and we’re excited to deliver for you! We’ve also made some quality improvements to our Spanish, French, German, and Italian engines – if you’ve tried these languages out in the past, give them another try and let us know what you think.

One more thing I wanted to mention - we try out various features from time to time, as part of our commitment to offer new ways for our users to take advantage of translation. You might notice that the link to get a professional translation has been taken down as part of our current release. We launched this service back in June 2008. This experimental feature has run its course (for now) and we are evaluating the experience to see how we could make it better. Stay tuned to this blog for updates, and of course your feedback is always appreciated!

Testing translation quality: Guest Blog

Microsoft Translator — Fri, 02 Jan 2009 18:42:16 GMT

Anand Chakravarty is an SDET on the Machine Translation team for the past 2.5 years, has been at Microsoft for 8 years, and was the first product tester on the MT team (and “still having fun with testing MT :-)”). Today’s guest blog is about testing translation quality.

---------------------------------------------------------------------------------------------------------------

One of the first points that comes to mind, when talking about verifying the quality of a translation system, is how do you measure the quality, or to be precise, the accuracy of translation? Translating between human languages using computers is a field that is almost half-a-century old. The area is challenging enough that even the best currently available machine translation systems are not close to obtaining linguistic quality that would be entirely satisfactory.

Part of the challenge is the many different data-points that humans process in order to understand the meaning of spoken/written text. There is the syntax, the parsing, the semantics, the context, the disambiguation, the reordering, all of which, and more, go into understanding a sentence. And this is just the sentence in 1 language. Now consider applying all of it to rebuild the sentence in another language and make it equally meaningful.

Some examples might help to make this point clearer. The term ‘Olympics 2008’ is fairly unambiguous. Similarly, one might expect the term ‘Elections 2008’ to mean the presidential elections in the USA. However, if the user is from, say, Canada, it would more likely refer to the local elections there.

A more general, and hence more common, example is a sentence like ‘The note was wrong’. Is the word ‘note’ a reference to an informative message or to a musical term? The proper translation depends upon context. Use more context, and your chances of getting a more accurate translation improve. This however comes at a cost: the more context the system tries to obtain, the slower its performance. Smart shipping decisions involve making the right balance between improving the accuracy of translation and delivering a workable translation result to users. Of course, both are important. The key is to understand where you direct efforts at improvement depending on how useful the end result is to the user.

This becomes particularly interesting when translating documents or web-pages, instead of just individual sentences. Let us say a translation request has been received for a web-page containing 100 sentences. Depending on the architecture of the translation system, these sentences could all go to one process, or be distributed across multiple processes/machines. Either way, it is clear that the time taken to translate this page in its entirety is proportional to the maximum time taken to translate a sentence. How long do we spend translating a sentence before that invested time becomes detrimental to the user’s time? In pursuit of the best translation, we might end up blocking the user from getting anything informative in response to their translation request. The utility of the system is thus governed by decisions that are made to balance linguistic quality and application performance.

With the Microsoft Translator product, there is the additional feature of our Bilingual Viewer, something unique among publically available translation products. It supports parallel text highlighting, synchronized scrolling and presents the page(s) with progressive rendering. This adds another layer to what our users see, and consequently another layer to polish and finish.

In the coming weeks, we hope to bring you more details of specific areas that were and are being tested to ship a top-quality translation system. Feel free to post any questions you have on this matter, something you always wanted to ask :-), in the Comments section.

A metal can (can’t it?): Guest Blog

Microsoft Translator — Thu, 18 Dec 2008 05:36:58 GMT

Lee Schwartz is a Computational Linguist on the Microsoft Translator team. Today’s guest blog is about getting lost in (machine) translation…

-----------------------------------------------------------------------------------

Recently, a user seemed upset with the translation he received for a metal paint can. No wonder. When he translated this into Spanish, he got un metal pintura puede, which means a metal paint is able to. And, what is that supposed to mean? But, then again, what is "meaning" to a machine translation system anyway? Does anything mean anything? Or, is the computer just seeing words in combination in one language and corresponding words in another language? And is it assuming that because one sequence is used in the source language when another is used in the target, one is the translation of another? Even if the machine translation program is just seeing words in combination, wouldn't it have seen paint can before and know that the can in this context is some kind of container? Then, again, can you be sure that the computer behind the MT program knows anything about paint cans, or has seen those two words in combination? Why do you think it would have? But, giving it the benefit of the doubt, and assuming it knows all about paint cans, or at least has seen the string paint can a lot, how is it supposed to know how to translate a metal paint can? Maybe the computer has seen something like The metal film on one side of the plate... may be obtained by ...spraying a metal paint or ....

Ah ha! So there really are metal paints. And, if there are metal paints, why can't a metal paint can be the answer to a metal paint can, can't it? Well, it is just not likely that when you have the words paint and can in sequence, that can means be able to. But then again it is just not likely that can means anything but be able to. I guess we can say things and think things that are just not likely. I can easily understand what A metal paint can can, can't it? means. The computer might just think that I inadvertently typed can twice. Certainly, if it learns from real data, say from the Web, it will see can can a lot. Maybe that is why it won't translate He did the can can correctly. But really, what is English doing with so many types of cans anyway? We can even can worms, but we won’t open that one now.