Common Questions (and Fears) or everything you wanted to know about MT but were afraid to ask

Implementations, free training programs and several domain-specific customized engines developed for our own use/clients have made us realize that there are several key questions, fears and misconceptions when companies, other LSPs, and even translators approach the use of MT.

Machine Translation is a hot topic. Gone are the times when translation companies could proclaim “machines will never match human quality”. Markets pressures and, above all, the need to speed time-to-market texts have turned the limelight on translation automation.  Several developments have even made it to the press, and the advent of free, general, plain text domain engines on the web like Google Translate, have put translation and fast language transfer high in the agenda for international businesses. President Obama’s call for the advancement and improvement of machine translation to help the world communicate and understand each better in October 2009 only made the subject gather more momentum (reports in the New York Times and The Economist, March 2010).

Yes, some translation technologies have been around for over 50 years, but how better are the newer technologies? how can MT be implemented successfully and integrated in a real-life production environment? What is the expected productivity increase and resulting cost saving? How will translators and staff react to the MT output? How can you manage it? As it happens with any innovation, there are fears and uncertainties … until a few success stories guide the way.

By answering the key 17 questions (or any others that you may have) we hope to provide enough information from experience and a few practical approaches on how to convert this new challenge into an innovative, competitive strategy.

If you have wondered or asked anyone any of the following questions, this will be a key section for you.

Q17 – Is your machine translation good with Czech language?

Q16 – How about data cleaning? What is your approach?

Q15 – In what way are you different from Google Translate?

Q14 – I deal with texts that are full of in-lines and tags. Most SMT systems only offer plain text and it takes a long time to copy and paste the in-lines/tags back in place. Have you done anything to solve this problem?

Q13 – What do you mean your system is built in open standards? What is the difference with other models?

Q12 – Are there any good (better, free) post-editing tools you can recommend?

Q11 – What about consistency? How do you ensure my company’s terminology prevails statistically over other options?

Q10 – Can you build any combination (for example Chinese or Japanese into Spanish or Russian)? What are the challenges?

Q9 – If I use MT, does that mean I cannot use my TM-based systems any more? Can you integrate MT with my TM-based software?


Q8 – What about “translator resistance” to become a post-editor?

Q7 – What is the ROI on an MT engine?

Q6 – What do you mean by re-training? Do engines need to be updated all the time, like TMs?  How much does it cost?

Q5 – Are savings in translation immediate?

Q4 – How much does post-editing cost?

Q3 – Will MT kill the need for a human translator?

Q2 – Why Statistical MT and not Rule-Based MT? What are the advantages and disadvantages?

Q1 – How many words do I need to build a good engine?