Watch pristine video:

I didn’t have space in today’s imprint story to have a portion an update on Microsoft’s translation efforts, which have been in the market — quietly — as antidote to nearly a year. The Microsoft Translator group is somewhat unexampled in that it’s still part of the Microsoft Research team, even though it’s a live product. That’s also why it was on display at the Microsoft Research Faculty Summit yesterday.

Microsoft is going up against the established online translator — Babel Fish, which Yahoo owns — and Google Translate.

Lane Rau, marketing manager for Microsoft Translator, demonstrated a side-by-side Web serving-boy translator that could be separately useful to people with familiarity, but not total comfort, in one more language. The “bilingual viewer” shows an first Web boy-servant on one half of the screen and a translated version on the other half. Holding the peer cursor besides a block of text highlights it on both pages for a like reason you can declare similar the translated text with the original.

I’ve played around with Babel Fish and Google Translate a bit to see if they have power to do the similar. If they can, it wasn’t obvious to me.

Another behold of Microsoft Translator shows the translated page in full and provides the commencement body in a small box when you hover the cursor over a text block.

It looks like a great tool for people learning a strange speech, and Rau said the service does get used that way.

But the contemplate of the bilingual viewer is to make machine translation usable now, even as researchers continue to improve it.

“You can represent since resembling sentence by proposition,” Rau said. “So, what that means is whether or not there is an misapprehension, for example my fame is Lane and that could be translated for example street in another language … you have power to go, oh, that was a name, so that’s why that mistake happened. And you can actually understand it a lot better.”

Microsoft is refining what’s called statistical instrument of force translation. It starts with millions of parallel sentences in tongue pairs gathered in a database. When a new sentence is entered against translation, the system looks through the database to select the most probable meaning or grammatical composition.

“It takes a ton of data — millions of sentences in parallel,” Rau uttered.

The crew is relying on its huge archive of professionally translated software documentation and also exploring other sources such as World Health Organization translations, she said.

Statistical machine translation differs from rule-based translation, which relies on exhaustive sets of rules for each power, manually entered by humans. Babel Fish uses rule-based change in the seat of a disease, powered by Systran, a French company.

Microsoft Translator also uses Systran as being standard, non-technical translations in some languages, Rau said. “We’re actually working without ceasing replacing that right now,” she added.

Systran was previously used by means of Google Translate, but according to private reports that surfaced last fall, Google switched off Systran and was using its own statistical instrument translation.

Most users still find plenty to fault with machine metastasis, be it statistical or rules-based.

Both Microsoft and Google see major benefits in the statistical road.

“It takes a long time to develop a good enough database of rules,” Rau said. “The nice thing about statistical translation is, once we get to that attribute level — we’re working adhering that upright now — it actually can tarry to improve and you can scale it across many more languages because you don’t have to regard the humans typing in manually different rules.”

Right now, Microsoft Translator offers about a twelve language pairs.

The company hasn’t conferred much marketing around its offering yet, focusing instead on improving the quality and integrating it into other products, such as Live Search. “We’re working on integrating it into Office,” Rau said.

Original text: http://blog.seattletimes.nwsource.com/techtracks/2008/07/microsoft_translator_quietly_making_progress_in_ma.html