Microsoft Translator team launched a new portal called “Language Labs,” featuring new experimental features and research prototypes from the Microsoft Translator research team.
As of today, you can try out following three experimental features on Language Labs: “Contextual Thesaurus, Translator Bookmarklet, and Universal Text Input”.
Microsoft Translator powers the translation service behind Bing, Microsoft Office, Internet Explorer, and recently Facebook and other global services like eBay and Trip Advisor, recently launched a new
Contextual Thesaurus is a prototype developed by Microsoft Research. Actually, it’s quite a bit more than that: it’s an English-to-English machine translation system that employs the same architecture that the Microsoft Translator uses when translating different languages.
To put it simply, i’s an English-to-English machine translation system that lets you explore alternate ways of expressing the same sentence, phrase, or idea.
How it differs from traditional thesaurus is that it provides synonyms or near synonyms for words according to its context. For example, try looking up the word “break” in a conventional thesaurus, then look up “businesses are asking for tax breaks” in the Contextual Thesaurus, and you will see the difference.
How do i user it: Go to Contextual Thesaurus. Type a short phrase into the input box. Then click the Submit button (the arrowhead in an orange circle) or hit the Enter key on your keyboard. The system accepts only one sentence at a time.
- Limit your input to 4-8 words. The system is capable of generating paraphrases much longer than that, but results will usually be more varied and interesting if you type in fewer words rather than more. Even two or three words will sometimes be enough to retrieve a useful set of equivalents.
- Formal language works better than colloquial language. Because our training data consists mostly of documents in the business, government, or technology domains, the system performs better on input related to these domains than it does on song lyrics or first-person blog posts.
- Click one of the paraphrases to highlight the path through the graph taken by that sentence.
- If you click on a word in the graph, the top-ranked paraphrase containing that term will be highlighted.
- If you click the check mark beside a paraphrase, the text will be moved into the input box in order to be paraphrased. This way you can round trip your paraphrases to see more alternatives.
Translator Bookmarklet lets you translate any page which just one simple click of a bookmark. Translation happens in place without leaving the page with this light-weight, cross-browser plugin.
You can try out the Translator Bookmarklet by going to here.
Universal Text Input (IME) lets you type any language with any keyboard on any web page. Input any language, any script, using only the Roman characters present on every keyboard.
You can try the service on IME site, and also install the Universal Text Input bookmarklet for your favorite browser including: Internet Explorer, Google Chrome and Firefox so that it works on any text box on the web.
To use, just “visit any web page and click the bookmarklet, ensuring the zoom is set to 100% (press Ctrl+0). Click in any text area and start typing. To disable/enable Universal Text Input, click on its icon in the text box.”
“Check your spelling as you go. For example type “helllo” then space and Universal Text Input will suggest you change that to “hello”. Use arrows to navigate to a correction then pick it by pressing space/enter or just start typing the next word.
Transliteration: Use English letters to phonetically type words in your language, and Universal Text Input will convert the letters for you. For example type “salam” to get the Arabic or “konnichiha” to get the Japanese. Type a word, use arrows to navigate to a transliteration and pick it by typing the next character- a space or a comma for example,” explains the site.
“For large parts of the world, not only is English not the primary language but the localized text is not even composed of Latin/Roman characters. Besides the fact that most IBM PC-standard keyboards only have Latin characters, it’s physically impractical to design one for languages such as Chinese with thousands of unique characters.
That’s where Input Method Editors, or IMEs, come in. Now an experimental Microsoft Translator Labs project “Universal Text Input” is beginning to port an IME to the web, independent of the operating system. Currently only a small set of languages are available: Arabic, Chinese, English, French, Greek, Japanese and Russian,” said Long Zheng.
To try out, “Language Labs”, visit the http://labs.microsofttranslator.com site!