Innovative technologies in localization

In preparation for the Loc Kit localization conference, we continue to communicate with speakers . This time we asked a few questions to the representatives of ABBYY Language Services Nadezhda Batiukova, the head of the multilingual localization department, and Anton Voronov, the director of innovation.

- Tell us about your work. What is it?

Nadezhda Batiukova: We localize software, websites, computer games, marketing materials in different languages, compile multilingual glossaries and conduct linguistic testing. Managers of the department interact with customers, select executors for projects, manage a multistage localization process and provide quality control.
')
- How is the localization process technologically built: with what technologies and software do you work?

Nadezhda: Localization is an interesting and complex task. We use various proprietary software products to optimize performance. Lingvo.Pro helps us manage terminology and centrally store all linguistic project resources. Many of our clients also use this solution to organize terminological work within their companies.

Since we work with different file formats, we constantly need to convert materials for CAT tools. Previously, for these purposes, our engineers created special utilities for each project. They helped extract texts for translating and calculating statistics, save code and tags, and automate the assembly of the file into the original format — that is, save managers from having to insert a translation into many languages ​​manually, line by line. We also used the development for automatic checks of the uniformity of terminology and the design of translations (no extra spaces, inconsistency of punctuation and register of letters in the original and final texts, etc.). Now the basis of automation is SmartCAT , which gradually replaces many individual utilities.

Anton Voronov: Localization is a multistage process, and the connection between all stages is especially important here. Now the main part of the translation processes in the company takes on SmartCAT. It acquires additional connectors, learns to work with different software, etc. The connectors, in turn, allow you to integrate the localization process with the code repositories. As we know, when developers create software, they write code and put it into a repository — for example, GitHub or SVN. Thanks to the connectors, as soon as the program gets into a specific repository and is ready for localization, you can proceed to transfer. You do not need to send anything by mail: we collect the source files in the repository, translate and place the finished text in the same repository. And developers can immediately build a localized version of the program.

- What languages ​​do you most often work with?

Nadezhda: We have more than 80 language pairs. We work with translators all over the world, and often localization is performed without the participation of the Russian language (that is, from one foreign language to another). Localization from English to the main European languages ​​- the so-called FIGS (French, Italian, German, Spanish) - is a basic set that is in demand among almost all of our clients. On average, there are eight to ten language pairs per project: FIGS, Polish, Czech, Turkish, and popular Asian languages ​​— Japanese, Chinese, and Korean. And this is not the limit: for example, for Hamsetrsoft, we regularly perform localization of software and materials for a site in 40 languages, and the absolute record holder in the number of languages ​​is a project for another of our clients: within the framework of this project we made localization into 100 different languages ​​of the world.

  - What interesting examples and features of localization into separate languages ​​have you met?

Hope: Curiosities usually happen when there are differences in the source and localized texts in the direction of the letter (from right to left, not from left to right), in the rules of punctuation or in the connotations of words (including the names of software products) with which not familiar customer. For example, somehow we persuaded the customer not to delete unusual punctuation marks from a file in Spanish, where, according to the rules of the language, question and exclamation marks are duplicated upside down at the beginning of a sentence.

Also in the process of localization, it is sometimes necessary to exclude certain realities from the text in order to adapt it to the target audience. For example, when working on one catalog in a version intended for Muslim countries, in agreement with the customer, everything related to alcohol and underwear was deleted. In another case, while adapting the American quiz for the Russian market, a number of topics were rewritten. In particular, baseball, not so popular with us, was replaced by figure skating.

  - How is the process of localization quality control built?

Nadezhda: Before starting the project, we compile a multilingual glossary: ​​we extract terminology from texts, translate into required languages ​​and approve it at the customer. If the client has his own glossary, then take it as a basis. Lingvo.Pro helps us to keep the terminology up to date, especially since the customer also connects to work directly in the solution interface.

We have a three-step work process: after the translator, the text is watched by the editor, then the proofreader. All performers are native speakers of languages ​​that are localized, residing in the respective countries. Under each language, we have our own teams of professionals: a separate team strictly for each subject. From experience, I can say: there is no such thing that one person works equally well with different languages ​​and topics - for example, he speaks Turkish, Japanese and Serbian in technical, legal and medical subjects.

The company also has a quality control department whose task is to train performers, regularly monitor the quality of completed orders, conduct examinations in any language of the world.

Finally, after all the stages of working on the text, we carry out the final automated checks using our own tools: we’ll see if everything is correct, if an extra comma has slipped, if the terms correspond to the glossary.

Anton: Since quality control is a very painstaking and thorough, but necessary work, it is very important to automate this process as much as possible. Therefore, in SmartCAT we are trying to pay special attention to this area: automatic checks are now in great demand. We are also working to ensure that users can view information in context and test how the translation will look in the interface - for this we develop special visualizers for various types of content.

- You mentioned linguistic testing. What is this service and does it have to do with quality control?

Nadezhda: Linguistic testing is the final stage of localization and an important component of the quality control process. The localized file is embedded in the real shell, and the expert evaluates it in context by viewing the screen behind the screen according to the approved plan. During testing, the specialist fixes all the shortcomings in a special form (bug report) and offers corrective options that are agreed with the customer and then entered into the work files. Linguistic testing is charged by the hour. Tariffs differ in languages ​​and depend on the cost of work of performers.

Unfortunately, in some cases, localization projects have urgency “yesterday”, so customers insist on skipping the testing phase. But, as practice shows, it saves a lot of time, which is subsequently spent, for example, on additional edits and approvals, when at the stage of final assembly it turns out that the text does not go along the length, etc.

  - How do you see the localization process in 5 years?

Anton: Today, there are several important trends in the industry - I think that in five years they will become more familiar to the localization process.

First of all, this is integration: a multistage localization process will be built on uniform solutions, the role of manual labor will be reduced, the success of projects will cease to depend on communication between the performers, and the content will be transmitted directly through the connectors.

The role of professional machine translation will increase: now many customers are afraid of MT with post-editing, because they think that this technology cannot give a qualitative result. Nevertheless, the future is in professional machine translation - with access to the linguistic resources of translation memory and glossaries, with setting up “engines”, post-editing and other processing stages.

The number of localization languages ​​will also increase. Previously, to be understood by 90% of the audience on the network, it was enough for 5-10 languages. Now, this will require 18-20 languages: more and more countries are going online, mobile technologies are developing, and the process of further globalization is underway.

The role of teamwork on localization projects will definitely strengthen.

- What do you think will be with the project manager in 5 years in such a world of automation?

Nadezhda: A good project manager in 5 years should already be a department head, at least J

There are cars with automatic transmission, but this does not mean that they can go without a driver. Similarly, with localization: we have SmartCAT, in which the project manager is more convenient to control the process. I am sure that the introduction of new technologies will not lead to a massive reduction in staff in localization departments. Rather, work will become more efficient and more time will be available for the development process.

Anton: I think localization project managers will be more deeply involved in the process and become more technologically competent. In general, they still understand the technological aspects better than managers of other translation departments, since they have not only linguistic, but also engineering competencies. Knowledge of professional translation software will lead to a different level of competition in the labor market. Therefore, if you work in a technology company, this is one thing, and if you do everything “on the knee” in the old manner, this is quite another.

  - How do you feel about using crowdsourcing?

Anton: We are positive about crowdsourcing. In the same localization, with the appropriate organization, it is possible to attract to the translation those people who are active users of the product, its fans, and almost more developers know about it. At the same time, they really want to benefit the product - this is the motivation of another level. One of the obvious advantages is that such translators are already immersed in context and are familiar with the subject.

In the professional scenario, we actively use teamwork and implement this direction in our products, thus laying the opportunities for crowdsourcing. For example, SmartCAT underlies the “Translate Coursera” - a project where volunteers translate lectures from the Coursera educational resource. The results can not fail to impress: these people translated the first million words in just 3 months. But at the same time, we understand that crowdsourcing raises many serious questions: this is the motivation of a large number of performers, the assessment of competence, and the management of the community, and the development of technology. We recently talked about this in detail in a special column on Slon.ru.

- Why did you decide to develop your own technologies for translation automation, and what results have you achieved at the moment?

Anton: A variety of specialized technological solutions for automating the translation process are beneficial at various stages of the process. But the real breakthrough begins when the entire localization process is continuously automated, from writing and extracting content to translator's work. At the same time, existing solutions are often heavy, difficult to master and adapt, and also do not always cope with rapidly evolving processes and tasks. Our company has always been distinguished by a high degree of automation of all processes, so a difficult choice was made in favor of developing a single solution to automate all aspects of a business. As a result, today we not only use these technologies within the company, but also offer the market in the form of our products: ABBYYSmartCAT, Lingvo.Pro, Perevedem.ru and others. It’s too early to talk about all the conclusions, but the first results we received indicate the correctness of the chosen path.