Menu

Understanding Machine Translation's Strengths

Last week, I wrote about being inspired by Kirti Vashee’s presentation on the application of statistical machine translation (MT). During this week, I had the chance to talk to several of our MT post editors about their views on editing MT output. It was very interesting to see their perspectives.

Post editing raw output is a different skills set than traditional editing of human translations.

As a starter, text selected for MT often tends to be “low visibility.” Mr. Vashee gave an example that for a travel review site, the four or five star hotel reviews are human translated while the lower star hotel reviews are machine translated with some human post editing.  Other low visibility text examples include car manuals that not everybody reads or web support content.  High visibility text such as marketing communications rarely if ever, gets selected for machine translation.

In the situation of translating low visibility text, particularly in technical communication, it is more important for the text to be technically accurate than stylish. It is a case where the translation sounding awkward but technically correct IS acceptable.

But translators new to post editing may be tempted to edit the text for not only accuracy but also flow and style. It leads them to spend more time than necessary on the text and they are more likely to complain about the quality of MT output. After all style and flow is not the strength of MT but speed and consistency is. It is important to have an agreement with the human post editors what is good enough (i.e. technical accuracy only, not style). Improved productivity and lower cost is also important to clients using MT. The best post editors understand this and can deliver high number of edited words per hour that meet quality standards.

One of wintranslation’s MT post editor commented, “When I have to review a translation, either done by a human or by a machine, I do not try to make it sound like if I wrote it.  I mostly correct errors, terminology inconsistencies, awkward style, problems with conveying the intended meaning and issues that really bother me.  If we are able to have that mindset, then it will be less cumbersome to review machine-translated text.  If we have the tendency to rewrite the translation, then the editing will be time-consuming and cumbersome.” It sums up the ideal attitude a post editor should have.

In terms of productivity gains, it varies from language to language. In Spanish and Portuguese for example where MT has made more inroads, one can reasonably expect a 50% productivity increase in terms of number of words translated per hour assuming the MT engine has been properly set up and trained. But gains are harder to come by in Asian languages.

(to be continued next week)