MT or CAT!

Machine Translation (MT) or Computer Aided Translation (CAT)!

      

Machine Translation (MT) is software that produces very raw, draft translations automatically and can also be referred to as automated translation.

Basically, MT performs simple substitution of words in one language (source) by words in another language (target), but that alone usually cannot produce a good translation of a text because recognition of whole phrases and their closest counterparts in the target language is needed.

Solving this problem with corpus statistical, and neural techniques is a rapidly growing field that is leading to better translations, handling differences in linguistic typology, translation of idioms, and the isolation of anomalies.

Machine Translation software requires extensive upfront glossary development, strict adherence to control source language authoring and qualified translators to post-edit the raw translations that are produced in order to achieve acceptable quality.

What does post-edit mean?

Post-editing is the process where humans amend machine-generated translation to achieve an acceptable final product.  Post-editing involves the correction of machine translation output to ensure that it meets a level of quality negotiated in advance between the client and the post-editor.

It is different from editing, which refers to the process of improving human generated text (a process which is often known as revision in the field of translation).

CAT tools!

Computer Aided Translation or Computer-Assisted Translation (CAT), is a broad term used to describe software that human translators use during the translation process to improve their productivity.

With a CAT tool, translators can work faster, eliminate repetitive translations, automatically correct mistakes, and achieve higher consistency of translations. Typical CAT tools are text editors that support bilingual file formats, and have built-in translation memory (TM) which is one of the most important functionalities of any CAT tool.

What does Translation Memory mean?

A Translation Memory  (TM) allows translators to reuse existing strings of text which have been previously translated. Such strings are stored within the TM’s database which accumulates on-going translated content allowing a translator to reuse content reducing the need to repeat themselves and to save consistency through the same document, therefore the larger the TM, the faster the translation process.

Such programs split the source text into manageable units known as segments. A source-text sentence or sentence-like unit (headings, titles or elements in a list) may be considered a segment. Texts may also be segmented into larger units such as paragraphs or small ones, such as clauses.

As the translator works through a document, the software displays each source segment in turn, and provides a previous translation for re-use if it finds a matching source segment in its database. If it does not, the program allows the translator to enter a translation for the new segment. After the translation for a segment is completed, the program stores the new translation and moves on to the next segment.

In conclusion, the translation memory is, in principle, a simple database of fields containing the source language segment, the translation of the segment, and other information such as segment creation date, last access, translator name, and so on.