Spam still lost in translation
Wednesday, May 20, 2009 | 03:30 PM ET
By Paul Jay, CBCNews.ca.
Yesterday Google announced that it was experimenting with GMail yet again, this time integrating the free email service with Google Translate, in what they say is a "step towards automatic email translation between 41 global languages."
The tool isn't perfect, but Google said they hope they can keep tweaking it to improve the quality of translation.
I ran a quick test this morning, asking for the French translation of this sentence: "My name is Paul Jay and I enjoy a piece of toast every now and then."
It spit back this: "Mon nom est Paul Jay et j'aime un morceau de pain grill de temps en temps." Hey, that's not bad.
Let's see what happens when I translate it back: "My name is Paul and I like Jay a piece of toast from time to time." Uh, oh.
This got me thinking about a conversation I had with Ryan Naraine over at Kaspersky Labs a month or so ago about why spam is so full of bad grammar.
One theory, which his employer Eugene Kaspersky offered during an interview last fall, is that since spam is so successful, there is no need economically to invest in making spam pitches more believable.
Naraine offered another theory: sending out a spam mailing can involve criminals from disparate parts of the world. As he said, a guy in the U.S. could be selling a product, but it could be a guy in Brazil that writes the malicious code and a botnet owner in Bulgaria who actually sends the message. At any or all of these steps, he says, the message could be created or altered.
So I thought I'd see how Google Translate would handle one of these messages. Here's the original message, using already somewhat garbled English (I've put a few asterisks where the company/product name is.)
An incredible opportunity to try out the worlds best selling ***. We are sending out FreeTrials paks of 16 of either *** or 8 of each. You decide which ones you want. Only catch is you must act fast as we can't keep giving these away forever. See ya there.
After putting it through Portugese and Bulgarian and then back to English, here's what we come up with:
A great opportunity to experience the best of worlds sales ***. We FreeTrials Paks of 16 or *** 8 each. You can decide which ones you want. Only catch is to act quickly as we can not keep them away forever. See you there.
This adds weight to my belief translation technology is behind our nonsensical spam. The new message includes the awkward "best of worlds sales" and the ironic "we can not keep them away forever." But on the plus side they converted "ya" to the more grammatically correct "you."
Google or someone else may end up improving this and make translation software into a true Babblefish.
But there is a part of me that hopes they don't ever get too good at it.
« Previous Post |Main| Next Post »
This discussion is nowOpen. Submit your Comment.
« Previous Post |Main| Next Post »
Post a Comment
Tech Bytes »
Recent Posts
- Universe hates Higgs boson, Chicago Cubs
- Friday, October 23, 2009
- Large Hadron Collider goes Back to the Future
- Monday, October 19, 2009
- Multi-touch concept for desktops: 10/GUI
- Thursday, October 15, 2009
- Finland makes broadband a legal right
- Wednesday, October 14, 2009
- Google Maps goes it alone
- Tuesday, October 13, 2009
- Subscribe to Tech Bytes
Archives
- October 2009 (10)
- September 2009 (13)
- August 2009 (12)
- July 2009 (15)
- June 2009 (10)
- May 2009 (18)
- April 2009 (17)
- March 2009 (13)
- February 2009 (11)
- January 2009 (12)
- December 2008 (10)
- November 2008 (10)
- October 2008 (9)
- September 2008 (4)
- August 2008 (4)
- July 2008 (16)
- June 2008 (9)
- May 2008 (12)
- April 2008 (15)
- March 2008 (13)
- February 2008 (13)
- January 2008 (47)
- December 2007 (12)
- November 2007 (12)
- October 2007 (17)
- September 2007 (18)
- August 2007 (17)
- July 2007 (27)
- June 2007 (18)
- May 2007 (28)
- April 2007 (25)
- March 2007 (28)
- February 2007 (25)
- January 2007 (35)
- December 2006 (25)
Comments
mt
Ottawa
This is interesting as a technology, but why exactly would I need a translator in my email? If I am receiving an email, that isn't spam, the sender should already know that my preferred language is English. If someone doesn't know me well enough to know what language I speak, then they have no business cluttering my Inbox!
All this really means is that people who do send spam won't need to go to the trouble of trying to translate their message before they send it to me. Gmail will enable me to receive spam in any language! Spectacular!
Posted May 21, 2009 09:39 AM
Carl Barron
c
Thats a good thing to do, yet the main problem I and my friends have with Gmail is that we cant use it much at all, the reason being theres no facility to create folders is there or have I missed something?
So its pretty useless, as having everything on one page would take you near enough forever to locate it in a busy e-mail box.
Signed Carl Barron Chairman of agpcuk
Posted May 21, 2009 04:53 PM
Monkey
Winnipeg
*cough* Babelfish *cough* its already a website *cough*
Posted May 25, 2009 06:43 PM
the dude
Not that this is GMail tech support but I thought I'd help out Carl.
Google has taken its big stick and beaten the IMAP protocol with it, deciding in its wisdom to replace folders with labels. In the GMail system a message is labelled, but when you interface with it via an IMAP-capable mail client, Google transmogrifies those labels and you see them as folders. So messages live in a big giant mailbox called All Mail and Google parses it all out using labels. So what you see in the Inbox are just messages in the giant all-holding All Mail mailbox labelled with 'Inbox'. Remove the 'Inbox' label and the message disappears from the Inbox pane, but lives on in All Mail.
So, in GMail just create labels and assign them to messages. I have labels for Friends, Carpet Cleaners and Bowling Tournaments. The cool thing is you can assign multiple labels per message, something you can't do with folders. Once you wrap your head around them, labels can be pretty flexible and fun to use, even though the dude doesn't like it when companies mess with open standards like IMAP.
Now, go make yourself a white russian and get in there. And to keep this slightly on topic, the dude agrees with mt and doesn't think this is perhaps the most efficient use of Google's resources.
Posted May 26, 2009 08:26 AM