Bohemicus 1.068 released!

What’s new:

  • improved machine-translation-marks remover, now removes also the AMT marks (adaptive machine translation, notably the ModernMT engine)
  • the machine-translation feature now sets the segments to draft status so that Trados Studio does not overwrite the machine-translated results
  • improved note-taking feature, added import-export for Evernote notes
  • fixed bug in invoicing – client and user data can now be updated directly from the Invoice window
  • improved invoicing – all invoices are now automatically saved into PDF
  • improved invoicing – a new grid view with all issued invoices is available on the Invoicing tab (you can now see all issued invoices at first glance)
  • improved invoicing – any issued invoice can now be clicked in the grid view to quickly show its contents and target folder where this invoice is stored
  • offline dictionaries can now be connected permanently
  • added explaining notes on individual cards
  • minor bug fixes

Removing the AT & NMT marks in Trados Studio

You can very easily remove those light-blue AT or NMT marks in machine-translated segments.

In Trados Studio right click your file(s) in target language and select “Explore containing folder“.

Drag and drop your file(s) onto Bohemicus, the XLIFF Pretranslate / Remove ATs tab (you can drag multiple files at once):

Click “Remove ATs”:

Wait for the removal process to complete…

Check your file in Trados Studio again… the AT marks have been removed:

You might also wish to watch this video:


How to translate 5000 words in 3 hours

Yes, this is indeed possible.

I remember those times 13 years back when translating 5000 words per DAY would be a major feat…. and I would feel completely exhausted, needing at least 2 days to recover from such a marathon.

Today, thanks to modern machine translation and voice dictation technologies, it is very well possible to translate 5000 words in just 3 hours…. and not to mentally collapse afterwards.

How to do it… in some reasonable quality

This is how it’s done in short: use machine translation and voice recognition.

Prerequisities

1. The text needs to be relatively easy to translate. It should have long fluent sentences with not too many specialized terms that would require any substantial research. A typical example would be a coffee-machine manual.

2. You need to have some experience as a translator so that you can quickly translate yourself those parts that do not come correct from the machine-translation engine. Also, you will need to understand the source language very well to quickly identify possible mistakes in the machine translation.

3. You need to be familiar with CAT tools. Ideally with SDL Trados or memoQ that have the actual potential to enhance translation productivity.

Or, sure, you can translate with one Word-document on the left, the other on the right. But this is very exhausting, as you have to steadily look with your eyes for the source text in your document. On the other hand, CAT tools have the advantage to neatly arrange individual sentences next to each other and to highlight the sentence (segment) currently being translated.

4. You will need some special technologies to achieve this goal. Especially the machine translation feature. Google Translate and DeepL provide very good results. You will to plug-in this into your CAT project, e.g. in SDL Studio 2011, this would be in Project Settings / Translation Memories and Automated Translation:

Alternatively, you can start Bohemicus and leave it running in the background. It will automatically deliver machine translation when you press the Ctrl+Space keyboard shortcut.

Step by step instructions

1. Prepare the project in SDL Studio (Trados) or memoQ. You can see this video to see how a project is prepared e.g. in memoQ (this video is on translating a webpage, but the preparation part is useful in this case too):

2. Connect the Google Translate / DeepL engine, see above. Or run Bohemicus.

3. Run your voice recognition software. You will need it when you translate segments (sentences) that come out as total nonsense from the machine translation engine. That’s because it’s usually faster to just dictate a sentence than to type it manually. At least for me  – I can type at some 200 chars/min… so it’s still faster to just dictate the text, instead of typing it. Also much more comfortable. You can also use e.g. the Bohemicus voice recognition software that works with 100+ languages (https://bohemicus-software.cz).

Summary

You will be basically reviewing the machine translated text, not actually translating. You can alternatively also use Bohemicus to machine translate and dictate your text (along with many other features that will make your translation process much easier). Bohemicus will enable you to use machine translation and voice dictation in just any CAT tool or any other Windows-based application.

Translating 5000 words in just 3 hours can be done. I know it. Because I have done it.

A final tip: Doing 5000 words in 3 hours can be exhausting, because you still need to process all those words with your brain. I suggest you eat well before you start working, to give your brain enough energy.

Please watch the video below to see this in action:

The Ctrl+Alt+Space shortcut and why you should definetely use it

The raison d’etre

The Ctrl+Alt+Space shortcut was originally conceived to deal with the formatting tags in SDL Studio, memoQ, Wordfast, XTM etc. That’s because Bohemicus cannot, at least for now, work with the formating tags and it will remove them when using the machine translation feature.

The basic idea

The basic idea of this shortcut: select the portion of text between these formating tags and press Ctrl+Alt+Space to translate such text. In this way, the formating tags will be preserved.

Online CAT tools

You can also take advantage of this keyboard shortcut when working with online CAT tools (SmartCat, Wordfast Anywhere, etc.) that are not 100% compatible with Bohemicus.

You can use this function in this way:

Copy all text from the source segment into the target segment (usually the Ctrl/Alt+Insert keyboard shortcut, but can be different – please check your CAT settings), select all text in the target segment (usually Ctrl+A), press Ctrl+Alt+Space. The selected portion of text (i.e. all text, because you have selected all text) will be translated.

You might also want to watch this video:

The top 10 features of Bohemicus I use every day

These are the 10 features of Bohemicus I use every day.

You can watch this video to see them in action:

1. Machine Translation

Machine translation can be used everywhere by just pressing a hotkey – Ctrl+Space to translate the whole segment in your CAT tool or Ctrl+Alt+Space to translate just the selected portion of text (this is especially useful in online CAT tools or in text-editor applications such as MS Word).

What I like about this: It works in 100+ languages, it is instantaneous (I don’t need to look for any options how to set it up in a CAT tool), it does NOT leave any traces, such as the AT/MT machine translation marks.

2. Speech-to-text

The speech-to-text (voice dictation) can be used in 100+ languages thanks to the Google speech-to-text engine in your Android phone. Please connect your Android phone, run Bohemicus both in your Android as well as in MS Windows, and start using the speech-to-text functionality to greatly improve your effectivity.

What I like about this: It works everywhere, in any CAT tools or text-editing applicaiton. The speech-to-text engine is very reliable and also works in noisy work environments.

3. Fast and convenient search in online/offline dictionaries and translations memories

Just select your term in whatever CAT tool you are currently working, and press Ctrl+Alt+K to quickly look it up in your connected offline/online dictionaries and translation memories.

What I like about this: The look-up process is fully automatic, Bohemicus will show all relevant windows on the screen without any need to leave your current CAT tool.

4. Fast and convenient googling

This works very much like the previous feature: just select your term and press Ctrl+Alt+G to search it with your preferred search engine.

What I like about this: It is fully automatic, Bohemicus will show the browser window with all the results looked up without you ever leaving your CAT tool.

5. Note taking

Select your term/sentence you would like to make a note of in your CAT tool and just press Ctrl+Alt+Shift+N to transfer the selected text into the Bohemicus note-taking tab.

What I like about this: It is very fast, can be done without too much clicking, and most importantly: I can create a whole block of notes that can be easily searched through, sent by email, edited etc.

6. Large files transfer

You can conveniently transfer large files of up to 100 MB with the large-files-transfer feature of Bohemicus. Simply right click your file and select “Send through the Bohemicus server” option. Your file will be instantly transferred to the Bohemicus server and a link to this file will be copied to clipboard.

You can then paste this link into an email and send it to your partner. Your partner can in turn click this link and download your file.

Why I like it: It’s slightly faster and more convenient than the competitors’ solutions, and you can add your own logo to the download screen.

7. Unit conversion

Unit conversion between the imperial and metric system has never been easier! Just select the value + its unit in the text and press Ctrl+Alt+F6/F7/F8 to convert it to your predefined units. You can set up to how many decimals you wish to round up the resulting value.

What I like about this: It’s very fast and easy, especially useful in long list of values that need to be converted between the imperial and metric system.

8. Quotation marks

You can very conveniently convert the default quotation marks into typographically correct quotation marks for your language on the fly.

What I like about this: You can set it up once and forget about it. Simply continue working in your CAT tool or in a text-editing aplication, pressing the quotation mark key on your keyboard any time you need. Bohemicus will always convert the marks to your typografically correct version on the fly. If you need to insert the U.S. qotation marks again, just press the Ctrl+Quotation mark key.

9. Clipboard manager

This is an immensely powerful feature: simply store frequently repeating strings into memory (up to 10 memory banks) and re-insert them from memory every time you need them, simply pasting them into your text.

What I like about this: I can easily see which string is stored where by just pressing the Ctrl key. I can also very easily store any string I choose by just pressing a hotkey combo (Ctrl+Alt+Shift+1…9,0), and then paste it into my text by pressing Ctrl+1…9,0.

10. Changing between uppercase and lowercase

You can very simply and quickly change just the FIRST letter in your segment to uppercase/lowecase, or change everyting to uppercase/lowercase by just pressing ONE keyboard combo.

What I like about this: It’s fast and convenient, works everywhere.


How to remove the machine-translation marks in every CAT tool

What are they?

As soon as you try to machine translate just about anything in any major CAT tool, such as Trados Studio, Across, WordFast…., you will notice that it will actually always leave a trace, a mark. You have those “AT” marks in Trados, “MT” in WordFast, a special icon along with a note in Across, etc. The only CAT tool that does not apparently leave any marks seems to be memoQ. Or at least I cannot see any.

No alt text provided for this image
No alt text provided for this image
No alt text provided for this image

Sometimes, such behavior might be undesirable.

How to get rid of machine translation marks

You can get rid of those marks in e.g. SDL Trados Studio by pre-translating the project again. What it means? After you finish your translation in this CAT, you just right click your file, choose Batch Tasks, then Pre-translate Files and then you choose the “Always overwrite existing translation”. This will translate your document and every segment will be replaced by its corresponding match in the translation memory. All “AT” marks will be overwritten by the “CM” mark (Context Match).

No alt text provided for this image
No alt text provided for this image
No alt text provided for this image

Not an ideal solution

This might be OK, but there can be some risks to it:

1) You are stressed, under time pressure, and you just forget to do it

2) You might complicate things greatly for your proofreader, becase he/she won’t be able to tell which segments to proofread. There will be no new segments, everything will be marked “CM” or “100%”.

I believe this tactics can be probably done in Across, WordFast and other tools as well, but cannot be sure, as I have not tried it. Also, I have tried the machine translation feature in Across, it its free translator edition, and it worked. But I believe, your project manager can disable the machine translation feature for you in Across project settings.

The ultimate solution

Yes, this is one of the advantages of this tool of mine. It does not leave any trace at all. Everything appears as manually translated. You can just press Ctrl+(Alt)+Space and have your segment machine translated without leaving any trace or mark.

What is means: You continue working in your CAT tool as usual (Trados, Across, WordFast…), but instead of taking advantage of your CAT’s machine translation feature, you connect your CAT to Bohemicus and press Ctrl+(Alt)+Space. Your segment will then be machine translated without leaving any trace or mark.

No alt text provided for this image

Recommendation

Of course, this might border on some work ethics. If your agency or customer expressly forbids you from using machine translation, because you are working on some classified document… then you should by all means respect their wish and also your professional ethics. I do not recommend online machine translation services in such cases.

What is the core idea of Bohemicus and how it can be useful to you

So, this is the core idea of Bohemicus: Let’s create an interface between you and your CAT tool. This interface should extend the capabilities of your CAT by a whole host of various features, thereby making you more effective and faster while translating your text in your CAT.

What it means in practice: Bohemicus will add the machine translation, voice dictation and many other features to e.g. the Across CAT tool that does not normally offer anything like that. You can then use machine translation, voice dictation in e.g. Across along with a whole host of other useful features. This functionality can be taken advantage of in virtually any CAT tool, be it Across, Transit, WordFast, memoQ, Trados Studio, XTM, Coach, Crowdin, Smartcat, etc.

The story

I remember that moment very clearly: It happened sometime in 2016 while I was working at a translation. I do have some problems with procrastination, so I left it for the very last moment, just like usual. And there I was: Some 5500 words to be translated in just 5 hours. I knew I would need the Google Machine Translation Plug-in for this. So I set it up in my Trados Studio and started working. I toiled my a*s off, but I was finally able to deliver at 12.00, which was the deadline for this job.

I was really exhausted, but it gave me a lot to think about. Wouldn’t it be great if I could just use such a plug-in in ALL CAT tools? Especially in Across, which I was using a lot during that period.

Machine translation… in just about any CAT tool

So, I started researching the internet to find how to do that. I knew I would need some technique how to manipulate a 3rd party application (i.e. my CAT tool) from my own tool. And sure enough, you can always rely on StackOverflow. The solution was quite simple: use the SendKeys method to simulate user keystrokes along with the Clipboard class to be able to copy out an open translation segment, process it in my own tool and then re-insert it back into my CAT tool.

Well, it sounds easy on paper, but took me many hours to tune this up to work reliably.

I then spent many more hours on figuring out how the Google translation API actually works. I was reading that Google’s tutorial all over again and again, but still couldn’t make it work. It was really frustrating. But then I realized I could just take the Google translation API URL, add the text to be translated, add my API key along with my source and target language and just send this to Google as a GET request and read and parse the returned message. And it worked!

Having figured out that SendKey thing along with these GET requests, the rest was just a piece of cake. Soon enough I was able to use machine translation in all of my CAT tools regardless on whether these CAT tools actually supported any machine translation or not. I literally forced them to use it anyway.

Dictating my texts

Then I concentrated on the other important feature of Bohemicus, the voice dictation, or voice recognition, if you will.

I had been using some voice dictation software before, but the problem was that it only had a limited vocabulary, and most importantly, it was very sensitive to noise. It only worked reliably when there was no surrounding noise. Cooking/boiling noise, radio, street noise… and the program started outputting nonsense. Also, I had to work with a headset, which was annoying.

Also, I should emphasize that I am a speaker of Czech, i.e. a minor language. And as you can imagine, major world software manufacturers do not really bother to support such a minor language, so e.g. the Dragon dictation software is out of question for me. On the other hand, Google reliably support 100+ languages, including Czech, Slovak, or Hungarian to name a few.

Android does the trick

But one day I realized that the Android system in my phone offers this voice recognition feature – I could just pose a question and the system would capture it and process accordingly. And it was surprisingly accurate, worked without a headset and tolerated a great deal of surrounding noise. So I said: Hey! Could this be somehow used also for my work?

So, I started researching the Android app market, or Google Play, as they say. There were some apps to capture voice and send it to PC as text, but they were clumsy to use or did not work at all, as they required a Bluetooth/Wi-Fi connection, but I was just not able to connect them to my PC.

Google voice recognition API was too expensive

I also started researching this Google voice recognition API…. and it turned out that I could actually use it in my PC no problem… the only issue was the price. It’s relatively expensive – for my usual volumes, I would pay some 150-200 EUR a month. And I certainly did not want that. So I returned to this original idea of leveraging the voice recognition feature in my Android phone and somehow sending it to my PC through Bluetooth or WiFi.

And soon enough I found some 30 lines of Java code that did the trick of activating the speech recognition routine in my Android phone.

Connecting Android to my PC

The remaining problem was the connection, i.e. how to send the converted text back to my PC. After briefly experimenting with a cable connection, I finally decided that Bluetooth and WiFi would be far more suitable. Luckily, research and coding was nothing more than a technicality. Sure, it took some time to tune up, but I made it finally work reliably.

The 2 above features were actually 2 separate software programs at the beginning. I then merged them into just one application, because it just seemed to make sense.

Adding more features

After having coded the 2 main features described above, I decided to add some more features. Especially a clipboard manager, insertion of correct quotation marks and some note-taking, those were the features I wanted the most. I will explain those in more detail in a later article.

Machine translation

Setting it up

Machine translation is very easy in Bohemicus. First, you need to set it up – enter your Google API key so that Google knows who to charge for the machine translation functionality (it is a paid service) or select the free alternative called MyMemory. If you don’t know how to obtain the Google API key, please read this article.

Enter the Google API key
…or use the free MyMemory alternative and enter you email so that you can increase your free translation quota

Also, select your source and target language:

Select your source and target languages

Using machine translation

And that’s it! You can now open your segment in virtually ANY CAT tool and just press Ctrl+Space. Bohemicus will retrieve your open segment, translate it behind the scenes, and re-insert the resulting translation back into your text.

Working with unrecognized target applications

Bohemicus is able to automatically recognise most offline major translation tools, e.g. SDL Studio, memoQ, DejaVu, Across, WordFast…. and translate the text seamlessly behind the scenes.

If your tool is not recognised, a warning will be displayed:

Bohemicus did not recognise your target application 🙁

Should this be the case, then simply select all text in your opened segment (usually the Ctrl+A keyboard shortcut, but it might be different for your particular CAT tool) and press Ctrl+Alt+Space to translate selected text only, i.e. all text in the segment, because you have selected all text.

Working with online CATs

You can also use Bohemicus with some online CAT tools. Just switch Bohemicus into the custom mode and select the keyboard combo your online tool uses to copy source text into the target segment:

Switch Bohemicus into the Custom mode when working with online CAT tools

Please read this article on how to work with online CAT tools in more detail.

You might also want to watch this video:

Machine translation with Bohemicus

Quick set-up

You should set up Bohemicus before you run it for the first time.

Set up the machine translation feature

First, please enter the Google API key for the machine translation feature. This key is needed for the machine translation feature to work, as Google needs this code so that they know who they should charge for the translation.

Enter your Google API key

If you don’t have this code, please read this chapter. In short: you need to create your Google Cloud account, sign in, create a new translation project, and finally get an API key.

Alternative: MyMemory

Alternatively, you can use the MyMemory service – it is free of charge up to 1000 words/day. If you wish to increase your quota, please enter your email address in the respective field:

Enter your email for the MyMemory service to receive the machine translation results free of charge

Set up your source and target languages

Next, please set up your source and target languages. Just select the corresponding language from the drop-down menus.

Speech-to-text (voice dictation)

Now, if you want to use the speech-to-text feature, you will need your Android phone or tablet. Speech-to-text feature works this way: you connect your Android device with your PC so that Bohemicus can take advantage of the Google speech-to-text engine in your phone/tablet and send converted speech to your PC.

Open the Google Play app and search for Bohemicus. Once you find it, tap to install this app.

Tap on Google Play Store
Find Bohemicus and install it into your Android device

Pair your Android device with Windows

Finally: you need to pair and connect your Android device with your PC. Please read this detailed article on how to do it through Bluetooth or this article for WiFi (Bluetooth is recommended).

In short: Turn on Bluetooth in your Android device and open the Bluetooth settings. Your device will scan your environment and offer any nearby devices. Click on your PC to pair it with Android.

Turn on Bluetooth
Tap your PC to pair it with your Android device
Confirm the Bluetooth pairing request in Windows

Launch Bohemicus both in Android and in Windows

Launch Bohemicus both in Android and in Windows. They should connect to each other almost immediately.

Android and Windows Bohemicus are now connected!

You are now ready to use Bohemicus to its full potential. Enjoy!

You might want to watch this video as well:

How to quickly set up Bohemicus and start translating

Working with online CATs

If you want to work with online CAT tools, such as SmartCat, XTM, Crowdin, Coach, etc…, just go to the Language&Settings tab and select the “Custom” option in the CAT tool section.

Select the “Custom” option to work with an online CAT

With this option checked, also select the keyboard hotkey combo that your CAT tool uses to copy the source segment into the target segment. Usually, this is Ctrl/Alt+Insert, but it can vary depending on the CAT tool you are using.

Select the keyboard combo you would use in your CAT tool to copy the source segment to the target segment

You can now work with your online CAT tool just like you would with an offline tool: just open your segment and press Ctrl+Space to machine translate its content.

Note: This works well in some CAT tools, such as SmartCat, Crowdin or XTM, but might have limited functionality in other tools (e.g. WordFast Anywhere) and not work at all (MateCat). If it does not work, simply open your segment, select all text in it (usually the Ctrl+A command) and press Ctrl+Alt+Space to translate selected text only = translate everything in your segment, because you have selected all text.

P.S. Yes, I know the picture is NOT funny… but we couldn’t resist anyway… 🙂