Leader in General Machine Translation Solutions
Trusted Translations has developed a technology process that integrates general machine translations, memory servers and post-editing services to produce high-volume output translations of the highest quality in the industry. Based on our client’s specifications and request, we will integrate a general machine translation solution with our quality control process to produce highly reliable and accurate translations. This proprietary system is designed to improve turnaround times significantly and to lower costs while maintaining translation quality at very high levels.
General Machine Translation Engines Use and Process
A General Machine Translation Engine (“GMTE”) refers to a software program that can translate text to and from a certain language with little or no human intervention. While each GMTE is built differently, most of them are designed to translate general content not involving specialized terminology – hence the name general machine translations. The most popular GMTEs are Google Translate, Systran and Microsoft Translator.
For overall comprehension of relatively basic content, GMTEs can do a decent job. However, as of this date, translations produced by GMTEs alone are not reliable enough for professional use as errors are almost inevitable even for simple documents.
With the above being said, GMTE can be a useful part of a translation process depending on the objectives of the client and the nature of the project. At Trusted Translations, we have learned how to leverage GMTEs and integrate them based on our clients’ needs and goals. If we believe a certain project is a good candidate to incorporate GMTEs into the process, we discuss the option with our client and design a solution that combines the benefits of GMTEs, memory servers and human translations.
Translation Memory Servers and General MT
The use of a Translation Memory Servers (“TMS”) when utilizing a GMTE can be a way to improve the overall quality of the translation output as it incorporates already human translated segments into the output. It is not as dynamic as a Customized Machine Translation Engine, however, it does allow you to leverage past translations to improve quality, consistency and output times. One possible configuration would have each content segment being translated first by means of a TMS. If an identical or similar segment is not found at this first step, then it is put through the General Machine Translation Engine. Finally, it might be also edited by an expert linguist. Any human post edits will be added to the TMS improving the quality of the next translation.
Human Post Editing of General Machine Translations
Utilizing a GMTE can significantly increase the speed of the output compared to a translation process involving only humans. With enough computing power, you could translate hundreds of millions of words in just a couple of days. The main problem lies in the quality of the final output. One solution is to add a human post-editing step or steps as part of the workflow. Integrating a human post-editing process does cut into the turnaround time but will provide a much higher level of quality and can help spot problem areas within a GMTE.
For certain types of projects, coupling human-post editing with a translation memory server step creates a viable alternative to a human only based approach.
General MT Engine, Memory Servers and Human Post Editing Workflow
Given that machine translation solutions are still in their nascent stages, Trusted Translations approaches each project differently. However, based on our experience, we have developed and tested several workflows that integrate machine translations successfully. The following is a common workflow that integrates GMTE with a translation memory and human post-editing solution.
As illustrated above, the content would flow through all steps of the process via an API or other connection. Each content segment will flow through the TMS and the General Machine Translation Engine up to the Post Editing Environment. In other words, the results of each segment coming out of our Translation Memory Server or General Machine Translation Engine will be post edited online by one of our professional linguists in our online Post-Editing Environment. The process would run simultaneously for multiple languages. The process flows almost instantaneously to the Post-Editing Environment and that results in automatic updates to the TMS.
General MT Versus Custom MT
The utilization of a General Machine Translation Engine combined with Translation Memory Servers significantly lowers cost by using Human Post-Editing instead of Human Translation and Revision. Turnaround times also improve dramatically. The drawback with this option is that the quality is not as high and it lacks the dynamic ability to learn as with the use of a Customized Machine Translation Engine.