Incorporating Machine translation into your Work

Posted on 02/08/17 in DCU, DCU LS NEWS, TRANSLATION, No Comments

While human translation is much better at expressing nuances and colloquialisms custom to localisation; machine translation can be beneficial and aid a translator with their workload when an approaching deadline is looming or to simply have handy particular phrases in a block of text translated in the same way you have done so in the past. Machine Translation has the ability to save certain phrases that you use time and time again in texts, saving you time and allowing the translator to work on the remaining text.

However, it is important that translators do not solely rely on their machines in order to create translations as this process of working is still in its infancy. Machine Translation was developed in the 1950s and has since then gone under research as the development of the internet accelerated the development of this software, for example as we see with Google Translate. The questions lie in whether non-sentient software can effectively and accurately reproduce a piece of text into another language.

While Machine Translation does speed up the process by providing key phrases that translators often use, it is not sufficient to merely exchange words in one language for equivalents in another: a translator must use their expertise in localisation and proofread that the text that has been translated is in the correct context. As languages are ever changing and developing; no two translators will arrive a precisely the same result, particularly where a more complex sentence or piece of writing is involved.

Translator x Machine Translation

To demonstrate, DCU Language Services asked some of its translators to provide their own rendition of a German sentence in English. The same sentences were also translated using some of the best-known translation software available on the internet: Google Translate, SYSTRAN, Bing (Microsoft Translator) and Babylon. From the outcomes below, it is possible to see the differences between the various translators’ interpretations of the original text, but also to observe the shortcomings of the translation software:

   Original Sentence

Der Widerspruch ist schriftlich oder mündlich zur Niederschrift binnen eines Monats nach Bekanntgabe dieses Bescheides bei der im Briefkopf genannten Stelle einzureichen.

   Translator 1

The appeal must be submitted in writing or orally for recording in writing within one month following issue of this notification at the offices specified in the letterhead.

   Translator 2 The appeal is to be submitted either in writing or orally to be put on record within one month after publication of this Notice, to the office designated in the letterhead.

   Translator 3 Objections are to be filed within a month of disclosure of this decision to the person named in the letterhead, verbally or in writing.

   Machine Translation 1 The contradiction is in writing or orally to the transcript within one month of the publication of this notification in the specified place in the letterhead submitted.

   Machine Translation 2 The contradiction is to be submitted in writing or verbally to the minute within one month after publication of this answer with the place specified in the letterhead.

In short, translators may often use Machine Translators while working on texts but it is also important to proofread over a completed text to ensure everything is translated in the idiomatic target language.