Believe it or not, we’ve been experimenting with MT and AI-related technologies for more than a decade. In the beginning, we experimented with Moses-powered statistical algorithms, and later on we explored what NMT-powered engines can do.

Ciklopea has always leaned into technology to help people work better and support clients in delivering localized experiences while saving time and money. Now we’ve been officially certified with ISO 18587, adding it to our range of existing norms (ISO 9001, ISO 17000, and ISO 27001).

This ISO standard establishes the qualifications post-editors must have, and the technical aspects involved in the post-editing process. We’ll review and correct the output generated by MT systems to make sure that 1) it meets the required quality standards and 2) fulfils its purpose.

The main benefit of MT lies in the fact that it automatically translates text or speech from one language to another. And while AI is great, it’s important to use it responsibly.

At Ciklopea, we are strong advocates for keeping humans “in the loop” to verify the raw engine output. Human post-editing is simply irreplaceable, especially from the standpoint of contextual understanding, subject matter expertise, handling uncommon languages and dialects, and more.

For certain projects, the ideal approach has proven to be a combination of human expertise and machine assistance. This is how you get accurate and culturally appropriate translations. Translated by machines. Verified by humans.

Maybe you’re looking for a way to optimize your translation budget through AI as well?

MT can help save up to 60% of translators’ time. This means two things for you as a client: 1) you will get translated content faster and 2) you will optimize your costs.

Schedule a call with Ciklopea and let’s explore post-editing together.

The post We Earned the ISO 18587 Certification for Human Post-Editing appeared first on Ciklopea.

It’s not yet possible “to insert a Russian book at one end and come out with an English book at the other,” says language scholar Prof. Leon Doster. But he’s predicted that translation fully done by a machine could very much be a reality in five, perhaps even three years. This has caused a series of headlines announcing a new world without language barriers and without… translators!

Don’t worry, robots won’t replace humans (yet)

Luckily for translators, the pioneers of machine translation trained their computers using a ‘rule based’ model. In order for a machine to understand a certain word or phrase and use it in translation, a set of rules had to be attached to each word. Such models were slow and complicated to create and computers were not learning fast. But the beginning of the 21st century, an increase in processing power, and a vast amount of new data brought with them a completely new technical approach: training machine models through statistical processes.

Fast forward to today, and computers use Natural Language Processing and Machine Learning. We have machines instantly translating documents and webpages. Travelers use apps to exchange information with locals wherever they go. An entire novel can be translated by a machine in about two minutes.

And yet, translators are still not extinct. On the contrary, they are in demand and needed more than ever.

Discussions of machines taking our jobs aside, technology and translators have been working side by side for decades now. Let’s explore a couple of cases when it’s better, as Agent Smith from the movie The Matrix would say, “not to send a human to do a machine’s job,” and where a machine is completely powerless.

AI and automation take care of repetitive taskTranslating large numbers of documents usually involves a lot of repetitive tasks. Let’s take the automotive industry as an example. Car manufacturers are often required by law to produce large amounts of straightforward, technical documents. Car manuals use simpler language and are highly similar to previous versions. As such, they are the perfect material for machine translation.

Paired with a skilled linguist to post-edit the translation, the machine doing the repetitive work and the linguist doing the fine-tuning, it’s a match made in heaven that ensures high-quality, speedy, and cost-effective translations.

Read about Ciklopea’s “continuous localization” process for Wallis Automotive

AI is great for terminology management

Spreadsheet glossaries are better than nothing, but terminology management is an area that can make especially good use of technology. Translation memories (TM) not only make translators’ lives easier by helping them work faster and more efficiently, but are also key in ensuring the material produced is highly accurate and consistent.

With AI in the form of a translation memory, any risk of inconsistency is reduced by automatically filling in the translated content where a repetition occurs. This allows translators to focus on maximizing translation quality.

The EU: a case study for machine translation

Imagine having a political union, with governing legal and executive bodies, a court of justice, a central bank and numerous other institutions, and 24 official languages! Well, that’s the European Union.

The EU Presidency Translator Project was born in 2015 when Latvia presided over the Council of the European Union. Machine translation was suggested as a solution for the masses of documents that all needed to be translated into 23 other languages, and the project was so successful that MT has been used since. Fully customized neural machine translation solutions were also developed to support the countries that presided over the EU Council in the years that followed.

The tool enables users to automatically translate texts, full documents, and local websites with the European Commission’s CEF eTranslation platform, which includes secure machine translation (MT) systems for all official EU languages. It is estimated that it saves EU institutions approximately 1 billion euros a year (not to mention making information more accessible in a shorter amount of time).

People are still needed for creative and literary translation

We’ve all seen hilariously out-of-context menu translations, or literal Google Translates of proverbs and word plays. Machines are becoming smarter but they just can’t learn how to be creative. When there’s ambiguity, word play, complex meaning, or creative copy, MT falls short. That’s why creative translators (transcreators) are still very valuable and in demand. The days when machines will be able to translate Shakespeare are still the stuff of science fiction.

What’s next? Real-time machine translation in the metaverse

At the beginning of 2022, Meta revealed they are building “the fastest AI supercomputer in the world”. It’s called RSC (Research SuperCluster) and researchers have already started using it to train large models for natural language processing and computer vision.

Its potential uses? According to Meta, it can be put to use in the metaverse, providing real-time voice translations for large groups of people, each speaking a different language, so they can seamlessly collaborate or play an AR game together.

Pretty interesting, wouldn’t you say? If you want to learn more about how you can use machine translation in your own projects, Ciklopea offers AI training as part of its consultancy services. Contact us today for more information on how to leverage machine translation to optimize costs and make the most of your human translators’ skills at the same time.

The post The intriguing history of machine translation appeared first on Ciklopea.

When it comes to machine translation there is still a lot of confusion, particularly for the people coming from the other industry fields. Naturally, they have a whole bunch of questions that need clarification, such as:

What does MT actually mean?

How does it work?

What do MT and CAT stand for?

Machine translation (MT) is a sub-field of computational linguistics that investigates the use of software to translate text or speech from one language to another. On a basic level, it works on a principle of simply converting the word from one language into the word of another. Therefore, as you can imagine, it cannot provide convenient translation, because the art of translating is much more complex. Since every language has its own rules and ways of usage, it is difficult to make machine translation tools do better than they’re doing now.

That’s why the human intervention is inevitable. We’re still the ones who are doing most of the work and we’re making all the necessary corrections, ensuring that translation output is efficient, correct and ready to use.

When we’re talking about machine translation there are several types worth mentioning:

Rule-Based Machine Translation (RBMT)

This type of machine translation requires more information about the structure of the source and target languages. Morphological and syntactic rules and semantic analysis of both languages help define the frame of rule-based machine translation. The process involves linking structures of input and output sentences using a parser, generator and a transfer lexicon. The problem with this method is that everything needs to be defined explicitly, which can be time consuming. If we want to speed up the whole process, we would hardly want to use this one.

Statistical Machine Translation (SMT)

This is a paradigm of machine translation in which the translation output is generated on the basis of statistical models whose parameters are derived from the analysis of bilingual text corpora. The idea is to store as many similar documents as possible in the same place so that tools can detect patterns in the documents that have previously been translated by professional human translators and to make guesses based on those findings. Google Translate was probably the most popular machine translation service that was using this method, but they have recently switched to neural MT models.

Example-Based Machine Translation (EBMT)

This method also relies on the corpus of previously translated documents. When we enter a sentence we want to translate, the sentences that contain similar sub-sentential components are selected from the corpus. Those sentences are then used to translate the subsentential components of the original sentence into the target language. You can already see that this simply screams for additional human intervention.

Hybrid Machine Translation (HMT)

Just as its name suggests, some of the previously mentioned techniques have their fingers in this. Hybrid machine translation ties together rule-based and statistical machine translation in a way that translations are performed using a rules based engine, which is then followed by statistical attempt to adjust and/or correct the output from the rules engine.

Neural Machine Translation (NMT)

Obviously, it has something to do with those “neural networks” we’re always hearing about, but we’re not going to torture you with unnecessary details. Not today, at least.

This type of machine translation is based on deep learning (artificial intelligence) and it has made rapid progress in recent years. As we said it above, Google has announced its translation services are now using this technology, abandoning the previously used statistical approach.

Stay tuned for an in-depth overview of Computer-Assisted Translation (CAT) coming very soon.

The post Science or Fiction: Machine Translation Explained appeared first on Ciklopea.

Fast forward sixty odd years, the MT is far more sophisticated and used daily by everyone, the human translators are still very much around, as well as the Atomic Era conviction that computers will eliminate the need for translators, or even the need to learn foreign languages at all – within a few short years. But will it?

Machines can replace some translators

There are translators who understand their job as a process of replacing words from one language to another, without being much concerned about the context, meaning, style and other elements of communication (while the communication of meaning between languages is the very essence of translation), and this is the type of translators than can be replaced by MT.

Simply put, machines can replace the people who translate like machines.

Computers are logical, people are not

Earlier this year, both Google and Facebook announced their shift from statistical machine translation paradigm to a new model based on neural networks. Statistical models mine bilingual text corpora for corresponding elements, but this material usually consists of formal documents composed in a standardized language that doesn’t have much in common with the everyday speech.

Succinctly speaking, the idea is to apply artificial intelligence and mine more informal data such as social media posts, with the purpose of communicating figures of speech, idiomatic expressions, regionalisms, slang and other spoken elements accurately between the languages.

While undoubtedly a giant step forward in the MT development the impact of which we have yet to see, one thing is certain – machines are logical and process language logically, while people are also irrational, emotional and imperfect and process language accordingly.

All these exclusively human qualities and limitations form a crucial part of communication, both verbal and non-verbal. An MT paradigm that will be able to replace human translators will therefore have to be able to operate on both logical and illogical levels at the same time. We cannot know what may happen in the millennia to come, but for the time being this doesn’t seem very likely.

MT is translator’s friend

Once upon a time, translators wrote on clay tablets. Then came papyri and quills, pens, notebooks, typewriters, personal computers and text editors, CAT tools and finally MT, and the development of technology has always been there to make the translation process easier, but never eliminated the need for professional human translators.

Machine translation is here and it will be here for a very long time. The growing demand for MT also means a growing demand for MT post-editing services. While machines do and will help us translate larger amounts of text for shorter periods, the translated materials do and will require a human touch – editing by a professional linguist.

Perhaps one day we will all be flying around the universe in personal spaceships with Babel fish stuck in our ears and communicating with the fellow terrestrials and extraterrestrials telepathically and we will no longer need translators and language teachers. But that day is still very, very distant.

The post Machine Translation, Artificial Intelligence and a Human Touch appeared first on Ciklopea.