This article describes the technology behind Lilt’s interactive translation suggestions. The details were first published in an academic conference paper, Models and Inference for Prefix-Constrained Machine Translation. Machine translation systems can translate whole sentences or documents, but they can also be used to finish translations that were started by a person — a form of autocomplete at the sentence level. In the computational linguistics literature, predicting the rest of a sentence is called prefix-constrainedmachine translation. The prefix of a sentence is the portion authored by a translator. A suffix is suggested by the machine to complete the translation. These suggestions are proposed interactively to translators after each word they type. Translators can accept all or part of the proposed suffix with a single keystroke, saving time by automating the most predictable parts of the translation process.
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.