Almost all professional translators use computer-assisted translation (CAT) tools. These are not the same as automated translation engines. They do not replicate or replace humans’ unique ability to interpret meaning. Instead, CAT tools augment human capabilities by doing what computers do best. They compare, store, and retrieve data. Understanding how these tools work provides insight into process and pricing for your localization projects.
At the start of a translation project, a linguist loads a document or batch of documents into a CAT tool. The interface presents the linguist with a two-column table of sentences or discrete segments of text. The source appears in one column and the space for the target translation appears in the other. These tools filter out formatting and other tags (such as HTML, XML, or tags used by design programs like Adobe InDesign) to hide them from the translator. This simplifies the project for the translator by presenting only the translatable text. It also protects the tags and code for documents, designs, software strings or webpages. This function allows the linguist to export the translated content with the original formatting intact.
If the project is a set of manuals to be translated from English into Spanish, for example, the English appears in the source column. The translator works by typing translations into empty target segments until the translation has been completed. A manual or other technical document often contains segments that appear multiple times. The CAT tool will auto-fill the phrase in the target column after the linguist translates it the first time. This saves time for the translator and ensures consistency. Also, the basic formatting of the manuals is preserved. (Some reformatting is always necessary because of text expansion and differences in the way languages look).
After the translation is finished and a second linguist has reviewed it, the project manager performs automated quality assurance. A major strength of CAT tools is their QA capability. This includes an array of functions to compensate for human error. These include internal spellcheck, of course. QA tools also find missing text or tags, deviations from approved terminologies and transposed numbers. For these tasks, the computer excels where humans struggle. For example, strict numeric comparisons across large data sets can be mind-numbing for a human proofreader. The QA components of CAT tools reveal in an instant whether the translator typed 892 in the target column instead of 829.
The final and most critical function of a CAT tool is the translation memory: a database of prior translations. What makes a TM different from a dictionary is the length of the units or segments that a TM saves and sorts. As a general rule, segments are made up of full sentences. TMs do not only store individual words, like a foreign language dictionary, nor do they simply store a few surrounding words. Instead, an entire segment in a source language is paired with its faithful translation in the target. A TM can also incorporate a term-base or bilingual glossary. These autosuggest pre-approved terms and their translations as a linguist works.
In our example, after running QA, finalizing, and delivering the translation, the CAT tool stores the validated English-Spanish pairs in a client-specific TM. Eventually an updated version of the manual will require translation. At that point, we load the revised English source back into the tool with the TM. The tool compares the source segments of the updated document with the source segments already on file. For each unchanged source sentence or segment, the target segment will auto-fill so the translator only needs to check the context, proofread, and validate it.
The TM also provides “partial” matches when the TM finds segments with differences of one or more words. Rather than translate the entire sentence, the linguist updates a word or two. The TM function works with all types of content. However, it generates the highest ROI for translations and updates of standardized documents such as legal/corporate documents, patent applications, software updates, and technical manuals.
Three key benefits of well-managed CAT tools flow directly to the client: cost savings, speed, and quality.
Before we quote a price for a new job, we use a CAT tool to analyze the source files. We look for at least two things. First, the number of repetitions of sentences or other freestanding text segments within the document or across a set of documents. Second, if we used a CAT tool to perform other translations into the same language for the same client, the TM will calculate whether any segments have exact or partial matches. Repetition and TM matches can lead to substantial discounts for the client as they allow the new documents to be partially pre-translated. Robust translation memories can reduce the billable word count of a job by 25% or more.
With the aid of a CAT tool, a translator can complete whole projects in much shorter time frames. They also allow for teamwork when a project requires fast turnaround. Translators can quickly review pre-translated content, allowing them to work through documents more efficiently. In addition, when translating a new segment that appears throughout the document or across a batch of documents, the tool will auto-fill that translation wherever the source segment appears. This ensures consistency when socially distanced teams of translators collaborate.
CAT tools allow the translator to focus on translation without worrying about the formatting of the files they have been asked to translate. For example, when localizing software, if you needed a translator who could also code, that would narrow the field and increase the price. CAT tools maximize the variety of file types for which a linguist can provide translation. As mentioned before, the QA function is invaluable for translation of any documents including numbers. Moreover, when standardized terminology is necessary throughout the text, the tools implement term-bases to ensure consistency.
As workers in the global economy become more comfortable working across multiple devices, new forms of CAT tools are beginning to appear. Many of these take advantage of cloud-based architectures. This new phase of collaborative translation technologies allows translators to work more efficiently in teams, increasing productivity while maintaining quality. Overall, CAT tools have greatly improved translator efficiency and accuracy. They also provide cost savings to the client. Their utility in the translation process will continue to grow.
As a language service partner, we are always alert to new technological solutions. However, human translators remain the foundation of quality work. When language providers lose sight of the human elements of translation and rely too much on the latest technologies, quality suffers. Scriptis built its business on respecting the art of translation. Technology enhances but does not replace human talent as the driver of accurate, compelling translations.