Tag: Translation Memory

memoQ 8.6 is Here!

memoQ 8.6 is Here!

memoQ 8.6 is our third release in 2018, and we are very excited about the new functionality it brings. The highlight of 8.6 is definitely the aim to pave the way to a more CMS-friendly translation environment, but like previous versions, it includes enhancements in many areas, including integration, terminology, productivity features, file filters, and user experience. Learn more about the most recent version and see how it will help you be even more productive.

 

Read full list of features.

Files, Files Everywhere: The Subtle Power of Translation Alignment

Files, Files Everywhere: The Subtle Power of Translation Alignment

Here’s the basic scenario: you have the translated versions of your documents, but the translation wasn’t performed in a CAT tool and you have to build a translation memory because these documents need to be updated or changed across the languages, you want to retain the existing elements, style and terminology, and you have integrated CAT technology in your processes in the meantime. The solution is a neat piece of language engineering called translation alignment.

Translation alignment is a native feature of most productivity tools for computer-assisted translation, but its application in real life is limited to very specific situations, so even the language professionals rarely have an opportunity to use it. However, these situations do happen once in while and when they do, alignment usually comes as a trusty solution for process optimization. We will take a look at two actual cases to show you what exactly it does.

Example No. 1: A simple case

Project outline:

Three Word documents previously translated to one language, totaling 6000 unweighted words. Two new documents totaling around 2500 words that feature certain elements of the existing files and need to follow the existing style and terminology.

Project execution:

Since the translated documents were properly formatted and there were no layout issues, the alignment process was completed almost instantly. The software was able to segmentize the source files and we matched the translated segments, with some minor tweaking of segmentation. We then built a translation memory from those matched segments and added the new files to the project.

The result:

Thanks to the created translation assets, the final wordcount of the new content was around 1500 and our linguists were able to produce translation in accordance with the previously established style and terminology. The assets were preserved for use on future projects.

Example No.2: An extreme case of multilingual alignment

Project outline:

In one of our projects we had to develop translation assets in four language pairs, totaling roughly 30k words per language. The source materials were expanded with new content totaling about 20k words unweighted and the language assets had to be developed both to retain the existing style and terminology solution and to help the client switch to a new CAT platform.

Project execution:

Unfortunately, there was no workaround for ploughing through dozens of files, but once we organized the materials we could proceed to the alignment phase. Since these files were localized and some parts were even transcreated to match the target cultures, which also included changes in layout and differences in content, we knew that alignment was not going to be fully automated.

This is why native linguists in these languages performed the translation alignment and communicated with the client and the content producer during this phase. While this slowed the process a bit, it ultimately yielded the best results possible.

We then exported the created translation memory in the cross-platform TMXformat that allowed use in different CAT tools and the alignment phase was finished.

The result:

With the TM applied, the weighted volume of new content was around 7k words. Our linguists localized the new materials in accordance with the existing conventions in the new CAT platform and the translation assets were saved for future use.

Wrap up

In both cases, translation alignment enabled us to reduce the volume of the new content for translation and localization and ensure stylistic and lexical consistencywith the previously translated materials. It also provided an additional, real-time quality control and helped our linguists produce a better translation in less time.

Translation alignment is not an everyday operation, but it is good to know that when it is called to deliver the goods, this is exactly what it does.

Reference: https://bit.ly/2p5aYr0

Machine Translation From the Cold War to Deep Learning

Machine Translation From the Cold War to Deep Learning

In the beginning

The story begins in 1933. Soviet scientist Peter Troyanskii presented “the machine for the selection and printing of words when translating from one language to another” to the Academy of Sciences of the USSR. The invention was super simple — it had cards in four different languages, a typewriter, and an old-school film camera.

The operator took the first word from the text, found a corresponding card, took a photo, and typed its morphological characteristics (noun, plural, genitive) on the typewriter. The typewriter’s keys encoded one of the features. The tape and the camera’s film were used simultaneously, making a set of frames with words and their morphology.

Despite all this, as often happened in the USSR, the invention was considered “useless”. Troyanskii died of Stenocardia after trying to finish his invention for 20 years. No one in the world knew about the machine until two Soviet scientists found his patents in 1956.

It was at the beginning of the Cold War. On January 7th 1954, at IBM headquarters in New York, the Georgetown–IBM experiment started. The IBM 701 computer automatically translated 60 Russian sentences into English for the first time in history.

However, the triumphant headlines hid one little detail. No one mentioned the translated examples were carefully selected and tested to exclude any ambiguity. For everyday use, that system was no better than a pocket phrasebook. Nevertheless, this sort of arms race launched: Canada, Germany, France, and especially Japan, all joined the race for machine translation.

The race for machine translation

The vain struggles to improve machine translation lasted for forty years. In 1966, the US ALPAC committee, in its famous report, called machine translation expensive, inaccurate, and unpromising. They instead recommended focusing on dictionary development, which eliminated US researchers from the race for almost a decade.

Even so, a basis for modern Natural Language Processing was created only by the scientists and their attempts, research, and developments. All of today’s search engines, spam filters, and personal assistants appeared thanks to a bunch of countries spying on each other.

Rule-based machine translation (RBMT)

The first ideas surrounding rule-based machine translation appeared in the 70s. The scientists peered over the interpreters’ work, trying to compel the tremendously sluggish computers to repeat those actions. These systems consisted of:

  • Bilingual dictionary (RU -> EN)
  • A set of linguistic rules for each language (For example, nouns ending in certain suffixes such as -heit, -keit, -ung are feminine)

That’s it. If needed, systems could be supplemented with hacks, such as lists of names, spelling correctors, and transliterators.

PROMPT and Systran are the most famous examples of RBMT systems. Just take a look at the Aliexpress to feel the soft breath of this golden age.

But even they had some nuances and subspecies.

Direct Machine Translation

This is the most straightforward type of machine translation. It divides the text into words, translates them, slightly corrects the morphology, and harmonizes syntax to make the whole thing sound right, more or less. When the sun goes down, trained linguists write the rules for each word.

The output returns some kind of translation. Usually, it’s quite crappy. It seems that the linguists wasted their time for nothing.

Modern systems do not use this approach at all, and modern linguists are grateful.

Transfer-based Machine Translation

In contrast to direct translation, we prepare first by determining the grammatical structure of the sentence, as we were taught at school. Then we manipulate whole constructions, not words, afterwards. This helps to get quite decent conversion of the word order in translation. In theory.

In practice, it still resulted in verbatim translation and exhausted linguists. On the one hand, it brought simplified general grammar rules. But on the other, it became more complicated because of the increased number of word constructions in comparison with single words.

Interlingual Machine Translation

In this method, the source text is transformed to the intermediate representation, and is unified for all the world’s languages (interlingua). It’s the same interlingua Descartes dreamed of: a meta-language, which follows the universal rules and transforms the translation into a simple “back and forth” task. Next, interlingua would convert to any target language, and here was the singularity!

Because of the conversion, Interlingua is often confused with transfer-based systems. The difference is the linguistic rules specific to every single language and interlingua, and not the language pairs. This means, we can add a third language to the interlingua system and translate between all three. We can’t do this in transfer-based systems.

It looks perfect, but in real life it’s not. It was extremely hard to create such universal interlingua — a lot of scientists have worked on it their whole lives. They’ve not succeeded, but thanks to them we now have morphological, syntactic, and even semantic levels of representation. But the only Meaning-text theory costs a fortune!

The idea of intermediate language will be back. Let’s wait awhile.

As you can see, all RBMT are dumb and terrifying, and that’s the reason they are rarely used unless for specific cases (like the weather report translation, and so on). Among the advantages of RBMT, often mentioned are its morphological accuracy (it doesn’t confuse the words), reproducibility of results (all translators get the same result), and the ability to tune it to the subject area (to teach economists or terms specific to programmers, for example).

Even if anyone were to succeed in creating an ideal RBMT, and linguists enhanced it with all the spelling rules, there would always be some exceptions: all the irregular verbs in English, separable prefixes in German, suffixes in Russian, and situations when people just say it differently. Any attempt to take into account all the nuances would waste millions of man hours.

And don’t forget about homonyms. The same word can have a different meaning in a different context, which leads to a variety of translations. How many meanings can you catch here: I saw a man on a hill with a telescope?

Languages did not develop based on a fixed set of rules — a fact which linguists love. They were much more influenced by the history of invasions in past three hundred years. How could you explain that to a machine?

Forty years of the Cold War didn’t help in finding any distinct solution. RBMT was dead.

Example-based Machine Translation (EBMT)

Japan was especially interested in fighting for machine translation. There was no Cold War, but there were reasons: very few people in the country knew English. It promised to be quite an issue at the upcoming globalization party. So the Japanese were extremely motivated to find a working method of machine translation.

Rule-based English-Japanese translation is extremely complicated. The language structure is completely different, and almost all words have to be rearranged and new ones added. In 1984, Makoto Nagao from Kyoto University came up with the idea of using ready-made phrases instead of repeated translation.

Let’s imagine that we have to translate a simple sentence — “I’m going to the cinema.” And let’s say we’ve already translated another similar sentence — “I’m going to the theater” — and we can find the word “cinema” in the dictionary.

All we need is to figure out the difference between the two sentences, translate the missing word, and then not screw it up. The more examples we have, the better the translation.

I build phrases in unfamiliar languages exactly the same way!

EBMT showed the light of day to scientists from all over the world: it turns out, you can just feed the machine with existing translations and not spend years forming rules and exceptions. Not a revolution yet, but clearly the first step towards it. The revolutionary invention of statistical translation would happen in just five years.

Statistical Machine Translation (SMT)

In early 1990, at the IBM Research Center, a machine translation system was first shown which knew nothing about rules and linguistics as a whole. It analyzed similar texts in two languages and tried to understand the patterns.

The idea was simple yet beautiful. An identical sentence in two languages split into words, which were matched afterwards. This operation repeated about 500 million times to count, for example, how many times the word “Das Haus” translated as “house” vs “building” vs “construction”, and so on.

If most of the time the source word was translated as “house”, the machine used this. Note that we did not set any rules nor use any dictionaries — all conclusions were done by machine, guided by stats and the logic that “if people translate that way, so will I.” And so statistical translation was born.

The method was much more efficient and accurate than all the previous ones. And no linguists were needed. The more texts we used, the better translation we got.

There was still one question left: how would the machine correlate the word “Das Haus,” and the word “building” — and how would we know these were the right translations?

The answer was that we wouldn’t know. At the start, the machine assumed that the word “Das Haus” equally correlated with any word from the translated sentence. Next, when “Das Haus” appeared in other sentences, the number of correlations with the “house” would increase. That’s the “word alignment algorithm,” a typical task for university-level machine learning.

The machine needed millions and millions of sentences in two languages to collect the relevant statistics for each word. How did we get them? Well, we decided to take the abstracts of the European Parliament and the United Nations Security Council meetings — they were available in the languages of all member countries and were now available for download at UN Corporaand Europarl Corpora.

Word-based SMT

In the beginning, the first statistical translation systems worked by splitting the sentence into words, since this approach was straightforward and logical. IBM’s first statistical translation model was called Model one. Quite elegant, right? Guess what they called the second one?

Model 1: “the bag of words”

Model one used a classical approach — to split into words and count stats. The word order wasn’t taken into account. The only trick was translating one word into multiple words. For example, “Der Staubsauger” could turn into “Vacuum Cleaner,” but that didn’t mean it would turn out vice versa.

Here’re some simple implementations in Python: shawa/IBM-Model-1.

Model 2: considering the word order in sentences

The lack of knowledge about languages’ word order became a problem for Model 1, and it’s very important in some cases.

Model 2 dealt with that: it memorized the usual place the word takes at the output sentence and shuffled the words for the more natural sound at the intermediate step. Things got better, but they were still kind of crappy.

Model 3: extra fertility

New words appeared in the translation quite often, such as articles in German or using “do” when negating in English. “Ich will keine Persimonen” → “I donot want Persimmons.” To deal with it, two more steps were added to Model 3.

  • The NULL token insertion, if the machine considers the necessity of a new word
  • Choosing the right grammatical particle or word for each token-word alignment

Model 4: word alignment

Model 2 considered the word alignment, but knew nothing about the reordering. For example, adjectives would often switch places with the noun, and no matter how good the order was memorized, it wouldn’t make the output better. Therefore, Model 4 took into account the so-called “relative order” — the model learned if two words always switched places.

Model 5: bugfixes

Nothing new here. Model 5 got some more parameters for the learning and fixed the issue with conflicting word positions.

Despite their revolutionary nature, word-based systems still failed to deal with cases, gender, and homonymy. Every single word was translated in a single-true way, according to the machine. Such systems are not used anymore, as they’ve been replaced by the more advanced phrase-based methods.

Phrase-based SMT

This method is based on all the word-based translation principles: statistics, reordering, and lexical hacks. Although, for the learning, it split the text not only into words but also phrases. These were the n-grams, to be precise, which were a contiguous sequence of n words in a row.

Thus, the machine learned to translate steady combinations of words, which noticeably improved accuracy.

The trick was, the phrases were not always simple syntax constructions, and the quality of the translation dropped significantly if anyone who was aware of linguistics and the sentences’ structure interfered. Frederick Jelinek, the pioneer of the computer linguistics, joked about it once: “Every time I fire a linguist, the performance of the speech recognizer goes up.”

Besides improving accuracy, the phrase-based translation provided more options in choosing the bilingual texts for learning. For the word-based translation, the exact match of the sources was critical, which excluded any literary or free translation. The phrase-based translation had no problem learning from them. To improve the translation, researchers even started to parse the news websites in different languages for that purpose.

Starting in 2006, everyone began to use this approach. Google Translate, Yandex, Bing, and other high-profile online translators worked as phrase-based right up until 2016. Each of you can probably recall the moments when Google either translated the sentence flawlessly or resulted in complete nonsense, right? The nonsense came from phrase-based features.

The good old rule-based approach consistently provided a predictable though terrible result. The statistical methods were surprising and puzzling. Google Translate turns “three hundred” into “300” without any hesitation. That’s called a statistical anomaly.

Phrase-based translation has become so popular, that when you hear “statistical machine translation” that is what is actually meant. Up until 2016, all studies lauded phrase-based translation as the state-of-the-art. Back then, no one even thought that Google was already stoking its fires, getting ready to change our whole image of machine translation.

Syntax-based SMT

This method should also be mentioned, briefly. Many years before the emergence of neural networks, syntax-based translation was considered “the future or translation,” but the idea did not take off.

The proponents of syntax-based translation believed it was possible to merge it with the rule-based method. It’s necessary to do quite a precise syntax analysis of the sentence — to determine the subject, the predicate, and other parts of the sentence, and then to build a sentence tree. Using it, the machine learns to convert syntactic units between languages and translates the rest by words or phrases. That would have solved the word alignment issue once and for all.

The problem is, the syntactic parsing works terribly, despite the fact that we consider it solved a while ago (as we have the ready-made libraries for many languages). I tried to use syntactic trees for tasks a bit more complicated than to parse the subject and the predicate. And every single time I gave up and used another method.

Let me know in the comments if you succeed using it at least once.

Neural Machine Translation (NMT)

A quite amusing paper on using neural networks in machine translation was published in 2014. The Internet didn’t notice it at all, except Google — they took out their shovels and started to dig. Two years later, in November 2016, Google made a game-changing announcement.

The idea was close to transferring the style between photos. Remember apps like Prisma, which enhanced pictures in some famous artist’s style? There was no magic. The neural network was taught to recognize the artist’s paintings. Next, the last layers containing the network’s decision were removed. The resulting stylized picture was just the intermediate image that network got. That’s the network’s fantasy, and we consider it beautiful.

If we can transfer the style to the photo, what if we try to impose another language to a source text? The text would be that precise “artist’s style,” and we would try to transfer it while keeping the essence of the image (in other words, the essence of the text).

Imagine I’m trying to describe my dog — average size, sharp nose, short tail, always barks. If I gave you this set of the dog’s features, and if the description was precise, you could draw it, even though you have never seen it.

Now, imagine the source text is the set of specific features. Basically, it means that you encode it, and let the other neural network decode it back to the text, but, in another language. The decoder only knows its language. It has no idea about of the features’ origin, but it can express them in, for example, Spanish. Continuing the analogy, it doesn’t matter how you draw the dog — with crayons, watercolor or your finger. You paint it as you can.

Once again — one neural network can only encode the sentence to the specific set of features, and another one can only decode them back to the text. Both have no idea about the each other, and each of them knows only its own language. Recall something? Interlingua is back. Ta-da.

The question is, how do we find those features? It’s obvious when we’re talking about the dog, but how to deal with the text? Thirty years ago scientists already tried to create the universal language code, and it ended in a total failure.

Nevertheless, we have deep learning now. And that’s its essential task! The primary distinction between the deep learning and classic neural networks lays precisely in the ability to search for those specific features, without any idea of their nature. If the neural network is big enough, and there are a couple of thousand video cards at hand, it’s possible to find those features in the text as well.

Theoretically, we can pass the features gotten from the neural networks to the linguists, so that they can open brave new horizons for themselves.

The question is, what type of neural network should be used for encoding and decoding? Convolutional Neural Networks (CNN) fit perfectly for pictures since they operate with independent blocks of pixels.

But there are no independent blocks in the text — every word depends on its surroundings. Text, speech, and music are always consistent. So recurrent neural networks (RNN) would be the best choice to handle them, since they remember the previous result — the prior word, in our case.

Now RNNs are used everywhere — Siri’s speech recognition (it’s parsing the sequence of sounds, where the next depends on the previous), keyboard’s tips (memorize the prior, guess the next), music generation, and even chatbots.

In two years, neural networks surpassed everything that had appeared in the past 20 years of translation. Neural translation contains 50% fewer word order mistakes, 17% fewer lexical mistakes, and 19% fewer grammar mistakes. The neural networks even learned to harmonize gender and case in different languages. And no one taught them to do so.

The most noticeable improvements occurred in fields where direct translation was never used. Statistical machine translation methods always worked using English as the key source. Thus, if you translated from Russian to German, the machine first translated the text to English and then from English to German, which leads to a double loss.

Neural translation doesn’t need that — only a decoder is required so it can work. That was the first time that direct translation between languages with no сommon dictionary became possible.

The conclusion and the future

Everyone’s still excited about the idea of “Babel fish” — instant speech translation. Google has made steps towards it with its Pixel Buds, but in fact, it’s still not what we were dreaming of. The instant speech translation is different from the usual translation. You need to know when to start translating and when to shut up and listen. I haven’t seen suitable approaches to solve this yet. Unless, maybe, Skype…

And here’s one more empty area: all the learning is limited to the set of parallel text blocks. The deepest neural networks still learn at parallel texts. We can’t teach the neural network without providing it with a source. People, instead, can complement their lexicon with reading books or articles, even if not translating them to their native language.

If people can do it, the neural network can do it too, in theory. I found only one prototype attempting to incite the network, which knows one language, to read the texts in another language in order to gain experience. I’d try it myself, but I’m silly. Ok, that’s it.

Reference: https://bit.ly/2HCmT6v

NEURAL MACHINE TRANSLATION: THE RISING STAR

NEURAL MACHINE TRANSLATION: THE RISING STAR

These days, language industry professionals simply can’t escape hearing about neural machine translation (NMT). However, there still isn’t enough information about the practical facts of NMT for translation buyers, language service providers, and translators. People often ask: is NMT intended for me? How will it change my life?

A Short History and Comparison

At the beginning of time – around the 1970s – the story began with rule-based machine translation (RBMT) solutions. The idea was to create grammatical rule sets for source and target languages, where machine translation is a kind of conversion process between the languages based on these rule sets. This concept works well with generic content, but adding new content, new language pairs, and maintaining the rule set is very time-consuming and expensive.

This problem was solved with statistical machine translation (SMT) around the late ‘80s and early ‘90s. SMT systems create statistical models by analyzing aligned source-target language data (training set) and use them to generate the translation. The advantage of SMT is the automatic learning process and the relatively easy adaptation by simply changing or extending the training set. The limitation of SMT is the training set itself: to create a usable engine, a large database of source-target segments is required. Additionally, SMT is not language independent in the sense that it is highly sensitive to the language combination and has a very hard time dealing with grammatically rich languages.

This is where neural machine translation (NMT) begins to shine: it can look at the sentence as a whole and can create associations between the phrases over an even longer distance within the sentence. The result is a convincing fluency and an improved grammatical correctness compared to SMT.

Statistical MT vs Neural MT

Both SMT and NMT are working on a statistical base and are using source-target language segment pairs as a basis. What’s the difference? What we typically call SMT is actually Phrase Based Statistical Machine Translation (PBSMT), meaning SMT is splitting the source segments into phrases. During the training process, SMT creates a translation model and a language model. The translation model stores the different translations of the phrases and the language model stores the probability of the sequence of phrases on the target side. During the translation phase, the decoder chooses the translation that gives the best result based on these two models. On a phrase or expression level, SMT (or PBSMT) is performing well, but language fluency and grammar is not good.

‘Buch’ is aligned with ‘book’ twice and only once with ‘the’ and ‘a’ – the winner is the ‘Buch’-’book’ combination

Neural Machine Translation, on the other hand, is using neural network-based, deep, machine learning technology. Words or even word chunks are transformed into “word vectors”. This means that ‘dog’ is not only representing the characters d, o and g, but it can contain contextual information from the training data. During the training phase, the NMT system tries to set the parameter weights of the neural network based on the reference values (source-target translation). Words appearing in similar context will get similar word vectors. The result is a neural network which can process source segments and transfer them into target segments. During translation, NMT is looking for a complete sentence, not just chunks (phrases). Thanks to the neural approach, it is not translating words, it’s transferring information and context. This is why fluency is much better than in SMT, but terminology accuracy is sometimes not perfect.

Similar words are closer to each other in a vector space

The Hardware

A popular GPU: NVIDIA Tesla

One big difference between SMT and NMT systems is that NMT requires Graphics Processing Units (GPUs), which were originally designed to help computers process graphics. These GPUs can calculate astonishingly fast – the latest cards have about 3,500 cores which can process data simultaneously. In fact, there is a small ongoing hardware revolution and GPU-based computers are the foundation for almost all deep learning and machine learning solutions. One of the great perks of this revolution is that nowadays, NMT is not only available for large enterprises, but also for small and medium-sized companies as well.

The Software

The main element, or ‘kernel’, of any NMT solution is the so-called NMT toolkit. There are a couple of NMT toolkits available, such as Nematus or openNMT, but the landscape is changing fast and more companies and universities are now developing their own toolkits. Since many of these toolkits are open-source solutions and hardware resources have become more affordable, the industry is experiencing an accelerating speed in toolkit R&D and NMT-related solutions.

On the other hand, as important as toolkits are, they are only one small part of a complex system, which contains frontend, backend, pre-processing and post-processing elements, parsers, filters, converters, and so on. These are all factors for anyone to consider before jumping into the development of an individual system. However, it is worth noting that the success of MT is highly community-driven and would not be where it is today without the open source community.

Corpora

A famous bilingual corpus: the Rosetta Stone

And here comes one of the most curious questions: what are the requirements of creating a well-performing NMT engine? Are there different rules compared to SMT systems? There are so many misunderstandings floating around on this topic that I think it’s a perfect opportunity to go into the details a little bit.

The main rules are nearly the same both for SMT and NMT systems. The differences are mainly that an NMT system is less sensitive and performs better in the same circumstances. As I have explained in an earlier blog post about SMT engine quality, the quality of an engine should always be measured in relation to the particular translation project for which you would like to use it.

These are the factors which will eventually influence the performance of an NMT engine:

Volume

Regardless of you may have heard, volume is still very important for NMT engines just like in the SMT world. There is no explicit rule on entry volumes but what we can safely say is that the bare minimum is about 100,000 segment pairs. There are Globalese users who are successfully using engines created based on 150,000 segments, but to be honest, this is more of an exception and requires special circumstances (like the right language combination, see below). The optimum volume starts around 500,000 segment pairs (2 million words).

Quality

The quality of the training set plays an important role (garbage in, garbage out). Don’t add unqualified content to your engine just to increase the overall size of the training set.

Relevance

Applying the right engine to the right project is the first key to success. An engine trained on automotive content will perform well on car manual translation but will give back disappointing results when you try to use it for web content for the food industry.

This raises the question of whether the content (TMs) should be mixed. If you have enough domain-specific content you shouldn’t necessarily add more out-of-domain data to your engine, but if you have an insufficient volume of domain-specific data then adding generic content (e.g. from public sources) may help improve the quality. We always encourage our Globalese users to try different engine combinations with different training sets.

Content type

Content generated by possible non-native speaking users on a chat forum or marketing material requiring transcreation is always a challenge to any MT system. On the other hand, technical documentation with controlled language is a very good candidate for NMT.

Language combination

Unfortunately, language combination still has an impact on quality. The good news is that NMT has now opened up the option of using machine translation for languages like Japanese, Turkish, or Hungarian –  languages which had nearly been excluded from the machine translation club because of poor results provided by SMT. NMT has also helped solve the problem of long distance dependencies for German and the translation output is much smoother for almost all languages. But English combined with Latin languages still provides better results than, for example, English combined with Russian when using similar volumes and training set quality.

Expectations for the future

Neural Machine Translation is a big step ahead in quality, but it still isn’t magic. Nobody should expect that NMT will replace human translators anytime soon. What you CAN expect is that NMT can be a powerful productivity tool in the translation process and open new service options both for translation buyers and language service providers (see post-editing experience).

Training and Translation Time

When we started developing Globalese NMT, one of the most surprising experiences for us was that the training time was far shorter than we had previously anticipated. This is due to the amazingly fast evolution of hardware and software. With Globalese, we currently have an average training time of 50,000 segments per hour – this means that an average engine with 1 million segments can be trained within one day. The situation is even better when looking at translation times: with Globalese, we currently have an average translation time between 100 and 400 segments per minute, depending on the corpus size, segment length in the translation and training content.

Neural MT Post-editing Experience

One of the great changes neural machine translation brings along is that the overall language quality is much better when compared to the SMT world. This does not mean that the translation is always perfect. As stated by one of our testers: if it is right, then it is astonishingly good quality. The ratio of good and poor translation naturally varies depending on the engine, but good engines can provide about 50% (or even higher) of really good translation target text.

Here are some examples showcasing what NMT post-editors can expect:

DE original:

Der Rechnungsführer sorgt für die gebotenen technischen Vorkehrungen zur wirksamen Anwendung des FWS und für dessen Überwachung.

Reference human translation:

The accounting officer shall ensure appropriate technical arrangements for aneffective functioning of the EWS and its monitoring.

Globalese NMT:

The accounting officer shall ensure the necessary technical arrangements for theeffective use of the EWS and for its monitoring.

As you can see, the output is fluent, and the differences are just preferential ones, more or less. This is highlighting another issue: automated quality metrics like BLEU score are not really sufficient to measure the quality. The example above is only a 50% match in the BLEU score, but if we look at the quality, the rating should be much higher.

Let’s look another example:

EN original

The concept of production costs must be understood as being net of any aid but inclusive of a normal level of profit.

Reference human translation:

Die Produktionskosten verstehen sich ohne Beihilfe, aber einschließlich eines normalen Gewinns.

Globalese NMT:

Der Begriff der Produktionskosten bezieht sich auf die Höhe der Beihilfe, aber einschließlich eines normalen Gewinns.

What is interesting here that the first part of the sentence sounds good, but if you look at the content, the translation is not good. This is an example of a fluent output with a bad translation. This is a typical case in the NMT world and it emphasizes the point that post-editors must examine NMT output differently than they did for SMT – in SMT, bad grammar was a clear indicator that the translation must be post-edited.

Post-editors who used to proof and correct SMT output have to change the way they are working and have to be more careful with proofreading, even if the NMT output looks alright at first glance. Also, services related to light post-editing will change – instead of correcting serious grammatical errors without checking the correctness of translation in order to create some readable content, the focus will shift to sorting out serious mistranslations. The funny thing is that one of the main problems in the SMT world was weak fluency and grammar, and now we have good fluency and grammar as an issue in the NMT world…

And finally:

DE original:

Aufgrund des rechtlichen Status der Beteiligten ist ein solcher Vorgang mit einer Beauftragung des liefernden Standorts und einer Berechnung der erbrachten Leistung verbunden.

Reference human translation:

The legal status of the companies involved in these activities means that this process is closely connected with placing orders at the location that is to supply the goods/services and calculating which goods/services they supply.

Globalese NMT:

Due to the legal status of the person, it may lead to this process at the site of the plant, and also a calculation of the completed technician.

This example shows that unfortunately, NMT can produce bad translations too. As I mentioned before, the ratio of good and bad NMT output you will face in a project always depends on the circumstances. Another weak point of NMT is that it currently cannot handle the terminology directly and it acts as a kind of “black box” with no option to directly influence the results.

Reference: https://bit.ly/2hBGsVh

How to Cut Localization Costs with Translation Technology

How to Cut Localization Costs with Translation Technology

What is translation technology?

Translation technologies are sets of software tools designed to process translation materials and help linguists in their everyday tasks. They are divided in three main subcategories:

Machine Translation (MT)

Translation tasks are performed by machines (computers) either on the basis of statistical models (MT engines execute translation tasks on the basis of accumulated translated materials) or neural models (MT engines are based on artificial intelligence). The computer-translated output is edited by professional human linguists through the process of postediting that may be more or less demanding depending on language combinations and the complexity of materials, as well as the volume of content.

Computer-Aided Translation (CAT)

Computer-aided or computer-assisted translation is performed by professional human translators who use specific CAT or productivity software tools to optimize their process and increase their output.

Providing a perfect combination of technological advantages and human expertise, CAT software packages are the staple tools of the language industry. CAT tools are essentially advanced text editors that break the source content into segments, and split the screen into source and target fields which in and of itself makes the translator’s job easier. However, they also include an array of advanced features that enable the optimization of the translation/localization process, enhance the quality of output and save time and resources. For this reason, they are also called productivity tools.

Figure 1 – CAT software in use

The most important features of productivity tools include:

  • Translation Asset Management
  • Advanced grammar and spell checkers
  • Advanced source and target text search
  • Concordance search.

Standard CAT tools include Across Language ServerSDL Trados StudioSDL GroupShare, SDL PassolomemoQMemsource CloudWordfastTranslation Workspace and others, and they come both in forms of installed software and cloud solutions.

Quality Assurance (QA)

Quality assurance tools are used for various quality control checks during and after the translation/localization process. These tools use sophisticated algorithms to check spelling, consistency, general and project-specific style, code and layout integrity and more.

All productivity tools have built-in QA features, but there are also dedicated quality assurance tools such as Xbench and Verifika QA.

What is a translation asset?

We all know that information has value and the same holds true for translated information. This is why previously translated/localized and edited textual elements in a specific language pair are regarded as translation assets in the language industry – once translated/localized and approved, textual elements do not need to be translated again and no additional resources are spent. These elements that are created, managed and used with productivity tools include:

Translation Memories (TM)

Translation memories are segmented databases containing previously translated elements in a specific language pair that can be reused and recycled in further projects. Productivity software calculates the percentage of similarity between the new content for translation/localization and the existing segments that were previously translated, edited and proofread, and the linguist team is able to access this information, use it and adapt it where necessary. This percentage has a direct impact on costs associated with a translation/localization project and the time required for project completion, as the matching segments cost less and require less time for processing.

Figure 2 – Translation memory in use (aligned sample from English to German)

Translation memories are usually developed during the initial stages of a translation/localization project and they grow over time, progressively cutting localization costs and reducing the time required for project completion. However, translation memories require regular maintenance, i.e. cleaning for this very reason, as the original content may change and new terminology may be adopted.

In case when an approved translation of a document exists, but it was performed without productivity tools, translation memories can be produced through the process of alignment:

Figure 3 – Document alignment example

Source and target documents are broken into segments that are subsequently matched to produce a TM file that can be used for a project.

Termbases (TB)

Termbases or terminology bases (TB) are databases containing translations of specific terms in a specific language pair that provide assistance to the linguist team and assure lexical consistency throughout projects.

Termbases can be developed before the project, when specific terminology translations have been confirmed by all stakeholders (client, content producer, linguist), or during the project, as the terms are defined. They are particularly useful in the localization of medical devices, technical materials and software.

Glossaries

Unlike termbases, glossaries are monolingual documents explaining specific terminology in either source or target language. They provide further context to linguists and can be used for the development of terminology bases.

Benefits of Translation Technology

The primary purpose of all translation technology is the optimization and unification of the translation/localization process, as well as providing the technological infrastructure that facilitates work and full utilization of the expertise of professional human translators.

As we have already seen, translation memories, once developed, provide immediate price reduction (that varies depending on the source materials and the amount of matching segments, but may run up to 20% in the initial stages and it may only grow over time), but the long-term, more subtle benefits of the smart integration of translation technology are the ones that really make a difference and they include:

Human Knowledge with Digital Infrastructure

While it has a limited application, machine translation still does not yield satisfactory results that can be used for commercial purposes. All machine translations need to be postedited by professional linguists and this process is known to take more time and resources instead of less.

On the other hand, translation performed in productivity tools is performed by people, translation assets are checked and approved by people, specific terminology is developed in collaboration with the client, content producers, marketing managers, subject-field experts and all other stakeholders, eventually providing a perfect combination of human expertise, feel and creativity, and technological solutions.

Time Saving

Professional human linguists are able to produce more in less time. Productivity software, TMs, TBs and glossaries all reduce the valuable hours of research and translation, and enable linguists to perform their tasks in a timely manner, with technological infrastructure acting as a stylistic and lexical guide.

This eventually enables the timely release of a localized product/service, with all the necessary quality checks performed.

Consistent Quality Control

The use of translation technology itself represents real-time quality control, as linguists rely on previously proofread and quality-checked elements, and maintain the established style, terminology and quality used in previous translations.

Brand Message Consistency

Translation assets enable the consistent use of a particular tonestyle and intent of the brand in all translation/localization projects. This means that the specific features of a corporate message for a particular market/target group will remain intact even if the linguist team changes on future projects.

Code / Layout Integrity Preservation

Translation technology enables the preservation of features of the original content across translated/localized versions, regardless of whether the materials are intended for printing or online publishing.

Different solutions are developed for different purposes. For example, advanced cloud-based solutions for the localization of WordPress-powered websites enable full preservation of codes and other technical elements, save a lot of time and effort in advance and optimize complex multilingual localization projects.

Wrap-up

In a larger scheme of things, all these benefits eventually spell long-term cost/time savings and a leaner translation/localization process due to their preventive functions that, in addition to direct price reduction, provide consistencyquality control and preservation of the integrity of source materials.

Reference: https://goo.gl/r5kmCJ

Adaptive MT – Trados 2017 New Feature

Adaptive MT – Trados 2017 New Feature


SDL Trados Studio 2017 includes new generation of machine translation.

How does it work?

It allows users to adapt SDL Language Cloud machine translation with their own preferred style. There is a free plan and it offers these features:

  • 400,000 machine translated characters per month.
  • only access to the baseline engines, so this means no industry or vertically trained engines.
  • 5 termbases, or dictionaries, which can be used to “force” the engine to use the translation you want for certain words/phrases.
  • 1 Adaptive engine.
  • Translator… this is basically a similar feature to FreeTranslation.com except it’s personalized with your Engine(s) and your termbases.

How does it help?

  • Faster translation with smarter MT suggestions.
  • Easy to use and get started.
  • Completely secure – no data is collected or shared.
  • Unique MT output, personal to you.
  • Access directly within Studio 2017.
  • No translation memory needed to train the MT.
  • Automatic, real time learning – no pre-training required.

What are the available language pairs?

Uptill now, Adaptive MT is available in these language pairs:

English <-> French
English <-> German
English <-> Italian
English <-> Spanish
English <-> Dutch
English <-> Portuguese
English <-> Japanese
English <-> Chinese

For reference: https://www.sdltrados.com/products/trados-studio/adaptivemt/