Cognitive Processes of Interpreting and Translation

by Marina Lee
2 Minute Read

Ever wonder what happens in the process of translation/interpretation “under the hood?” Let’s look at the mode of interpretation first. Cognitive processes that take place in a simultaneous interpreter’s mind and brain are intense and all happening nearly at the same time. Neurons are firing in all directions, igniting different cognitive processing circuitry. The brain is literally “on fire,” as a Russian cognitive scientist puts it.

Consecutive interpreting is different from simultaneous from the perspective of the cognitive science, in that the stages of conversion of meaning and reproduction are delayed from the stage of intake and deciphering of the message. That does not, however, make the process easier.

In consecutive interpreting, an additional cognitive function is activated, memory. This mode of interpretation relies on this function rather heavily. As the interpreter makes notes in a form of shorthand signs and symbols which denote subjects, objects, and predicates, they also have to understand and remember the logical connections between the segments. A well-trained interpreter’s memory may allow one to retain very large volumes of information and to be able to retrieve it quickly while the interpreter is producing the communication in the target language. This memory is short-term: once the task is done, the information is “erased,” making space for new information.

Translation process is different from interpreting in that it relies on written text. Sight translation, although done orally, is considered to be a part of the translation mode because input is received from the written text (and memory is activated in a different way).

Cognitively, translation process involves the same major steps: decode the source communication, convert/recode it into the target language, produce target-language communication.

The translation process does not use the rapid-access short-term memory or the simultaneous processing and output of information quiet as heavily. Because the translator has the text available and more time to research and investigate before making translation decisions, they may not need to retain large amount of information in their short-term memory. Instead, they are reaching deeper. This especially pertains to any content where subject matter and language require stylistic skill and aptitude. Wherever metaphorical devices or style figures are used, the translator’s task is to reach for the associative fields, the symbolic arsenal, and the existing cultural metaphors of their target language to select an equivalent or, if one cannot be found (as they rarely are), to construct a new one. Ability to translate and express messages in an efficient (apt, clear, faithful) and stylistically appropriate form are its own type of intelligence — a linguistic IQ.


Interactive and Adaptive Computer Aided Translation

5 Minute Read

Originally published on Kirti Vashee’s blog eMpTy Pages. Lilt is an interactive and adaptive computer-aided translation tool that integrates machine translation, translation memories, and termbases into one interface that learns from translators. Using Lilt is an entirely different experience from post-editing machine translations — an experience that our users love, and one that yields substantial productivity gains without compromising quality. The first step toward using this new kind of tool is to understand how interactive and adaptive machine assistance is different from conventional MT, and how these technologies relate to exciting new developments in neural MT and deep learning. Interactive MT doesn’t just translate each segment once and leave the translator to clean up the mess. Instead, each word that the translator types into the Lilt environment is integrated into a new automatic translation suggestion in real time. While text messaging apps autocomplete words, interactive MT autocompletes whole sentences. Interactive MT actually improves translation quality. In conventional MT post-editing, the computer knows what segment will be translated, but doesn’t know anything about the phrasing decisions that a translator will make. Interactive translations are more accurate because they can observe what the translator has typed so far and update their suggestions based on all available information.

Read More
pexels-photo-373543 (1)

Here's Why Neural Machine Translation is a Huge Leap Forward

4 Minute Read

  Though machine translation has been around for decades, the most you’ll read about it is the perceived proximity to the mythical “Babel Fish” --an instantaneous personal translation device-- itself ready to replace each and every human translator. The part that gets left out is machine translation's relationship with human translators. For a long time, this relationship was no more complex than post-editing badly translated text, a process most translators find to be a tiresome chore. With the advent of neural machine translation, however, machine translation is not just something that creates more tedious work for translators. It is now a partner to them, making them faster and their output more accurate.

Read More