Need to translate a PDF file? Google Translate does it for you

Oct 17

Update (3.3.2011). Google Docs now supports OCR and translation of PDF files. Read about it here.

Translation of PDF files can be challenging. The text is often uneditable, making it impossible to run it through one of the automatic translation tools. Today I did some tinkering with Google Translate and found something I did not know previously: you can use Google Translate for translation of PDF files. So if you get a file that is in PDF format, such as an RFQ or a proposal, you can get Google to translate it for you in one click. Here’s how to do it:

In Google Translate, click Choose File. Then select the PDF file you want to translate. Then click Translate. After a few moments the translation is displayed in a browser window in HTML format. You can then select the text (e.g. Ctrl-A) and paste it into a MS Word file for editing and formatting.

I tried this out on a few PDF files and the results were very reasonable. Of course the result depends on the quality of the PDF file you start with; if you translate a scanned file or a fax which is lousy to begin with, it probably won’t go over well in Google Translate.

For now, PDF files are not supported in the Google Translator Toolkit but I would imagine that the folks at Google will make an announcement soon that PDF files are supported, as it appears that they have the technology in place to convert PDFs to text/html format.

Another way to translate PDF files is to use an OCR application to convert the PDF file to RTF and then to upload it to Google. We use an application called ABBYY PDF Transformer which usually does a good job of converting PDF files to text format.

Englisch übersetzer, English Übersetzungen

Would you like a quote for professional translation of a PDF file? Send it to
info@gts-translation.com.

none

Translate to:

My tweets

RT @MVDtranslations: RT @tolkenselect: 10 top don’ts when ordering a translation http://t.co/Df3ViGTw #vertalen #vertaler #vertaling #klant 1 day ago

@hansfens Good to have you aboard Twitter Hans, hope you are doing well! 2 days ago

GTS Translation Plugin » WordPress AddOns http://t.co/HtvKxQ9p 4 days ago

@DutchTranslat you are gorgeous,thanks for following me 4 days ago

RT @phillipswindle: Positive thinking evokes more energy, more initiative and more happiness. ~ #PHIL 6 days ago

Comments

Leah Aharoni

October 17th, 2010 at 12:49 PM

Make sure you are not signed on an NDA before sharing your client’s files with Google. Otherwise you are violating the agreement. Google DOES collect the information submitted via Translate and other services. You can read more about it here: http://aqtext.com/blog/google-translate/
Dave

October 17th, 2010 at 1:01 PM

Thanks Leah, I read your blog post. Most of the information you wrote is already known to many people but your comments about NDA violation through use of Google Translate is something most people probably overlook. Point well taken. Best, Dave
PDF to Word

October 18th, 2010 at 2:10 AM

As you said Dave you convert pdf files into text with ABBYY PDF Transformer but its cost is $79. Why not you try quick pdf to word which comes in only $29.95?
Philippe

October 19th, 2010 at 4:26 AM

Really thanks for the input about Google Translate!
Vince

October 19th, 2010 at 1:08 PM

Hi! I was just visiting http://www.gts-translation.com/nationalholidays/export-calendar.asp. It’s a great website! Thanks.
MS Word Expert

October 19th, 2010 at 1:32 PM

Thakns for this informative post, additionally I want to say that a translation feature new to Microsoft Word 2007 that—obviously enough—translates highlighted text directly in Word. To use it, highlight your to-be-translated text, head to the Review ribbon, and click the Translate button. Word can translate either the entire document or just your selection, and it does it through an online translation service. The number of available languages is impressive, so you should be able to translate virtually anything you need.
Philippe

October 19th, 2010 at 8:45 PM

@MS Word Expert: is this feature storing any information somewhere online?
Frank

October 20th, 2010 at 8:40 AM

There are many web-based OCR solutions without need to registration. Here a good one I’d like to recommend you: http://www.goodocr.com
Mark

October 24th, 2010 at 1:51 PM

Having mentioned OCR, there is a totally free online optical character recognition service, and it’s very accurate. I use it all the time: http://www.free-online-ocr.com
Dave

October 26th, 2010 at 1:03 AM

Thanks to everyone who commented about OCR tools for PDF to RTF conversion. It would be a good idea for someone to blog about the various tools and provide unbiased product reviews and comparisons. If someone does write such a post, please let me know so I can link it up to the GTS blog.

Just a side note: I tried to use Google Translate to convert PDFs to RTF by selecting English to English translation, but Google displays an error message saying that “English to English translation in not supported.”
carl

October 26th, 2010 at 1:45 AM

good tool for ocr and translation from pdf http://www.traductornano.com/ayuda/como-traducir-un-pdf.aspx
cümle çevir

October 26th, 2010 at 5:09 PM

thanks I read your blog post , cümle cevir
Frank

November 2nd, 2010 at 8:14 AM

I was looking for a free document scanning software on the internet. I had used Textbridge for the past 8 years with many versions of Windows OS and I was not willing to buy another expensive scanning software any more. Then I found some interesting ones online, like Free OCR, etc. Though not as good as commercial OCR softwares, they did produce promising results to me.
Harry

November 12th, 2010 at 2:02 AM

It’s not until recently when I find it is possible to do character recognition online, for example with the site Free OCR. This site helped me work today to convert an image file (like tif files ) to readable text. The result is not bad.
How to convert your blog posts into more sales | GTS Blog

December 5th, 2010 at 6:28 AM

[...] give you an example from my own GTS blog: last October I published a blog post entitled: Need to translate a PDF file? Google Translate does it for you. This post was read well over 1,000 times and is read by an average of 30 different people a day. [...]

GTS Blog