Archives for March 2024

Validation – high-quality translations are a joint effort

27.3.2024 by Jari Herrgård

Successful translations require teamwork. Although the key person in the translation process is the translator and their tools, they alone are not able to achieve ideal quality. In the translation process, the best possible result always requires input from the translation agency’s other employees as well as the customer. Validation is perhaps the most important tool for assessing the linguistic quality of translations.

If you are a customer, you may be asking why you should contribute to the process – it’s our job, after all. You are correct and, as a customer, your involvement is not obligatory. But if you want the best result, it is in your best interest to participate in the process – especially through feedback.

To some extent, language is a matter of opinion. We are all fluent in at least our own native tongue, and many of us also know several other languages. Therefore, we all have a lot of opinions about language. This is especially true in work contexts if language plays a central role in our work and we put a lot of thought into how a message should be conveyed. We know how we want to address the reader, and perhaps the organisation we work in has even defined common rules for what kinds of images we should evoke.

Even if these rules are self-explanatory within the organisation and come naturally to you, they may not be self-evident to the translator. The translator is always a bit of an outsider and depends on what they are told about your preferred language and its nuances. This is where teamwork comes into play: the ideal translation process involves cooperation to ensure that the translation matches the customer’s communication needs as closely as possible. By providing feedback on the translations, the customer can ensure that each translation is better than the one before and closer to the customer’s ideal.

Validation as a tool

One of the most important tools for the process described above is validation. This means a review by the customer after the translation has been completed. It may often be carried out by an expert whose main work tasks do not include translation. The expert is responsible for checking, in particular, the terminology and style, and assessing whether they are in line with the customer’s brand. Other review work can also be done at the same time.

Validation in itself is a simple step, and there is no doubt about its usefulness, but it is still often skipped altogether. Typically, validation is carried out by sending PDF or DOCX files to vendors or technical experts, for example. The expert will use the comment or track changes functions to add their own comments and corrections to the document. These will be included in the final version and imported into the translation memory by the translation agency. This process is quite laborious and may complicate version control, which are the main reasons why it is often skipped.

Validation with system support

At LanguageWire, workflow and translation work are based on a shared platform used by customers, translators and internal project managers. Using a single platform has many benefits, especially in terms of translation project communications and transparency.

The validation step also takes place entirely on this platform, which makes the process quick and efficient. Usually, the validation step is added as soon as the project is created.

Validation takes place after the translators have done their work. The experts assigned to the project will receive an automatic message from the system and, by clicking on the link, they will be forwarded to the right project. There is no need to search for the project or upload any files, and the expert can start working in their browser right away.

Validation is done in the same tool that the translators use, and the validator has access to all the same information. This means, for example, that they will automatically be able to view the correct terminology if there is a glossary attached. This helps to avoid situations where outdated or otherwise incorrect terminology is used in the text during the validation phase. The validator also has access to other tools, such as proofreading and translation tools. Our user-friendly interface ensures that you do not need to be a professional translator to benefit from the translation platform. Everything you need can be done with basic browser skills.

In addition to possible corrections, the validator can also communicate with the translator, which helps to quickly solve potential dilemmas. Since everyone works in the same digital environment, all corrections are also saved directly in the translation memory, and they do not need to be separately exported at the end of the project.

In order to ensure the best possible translation quality and that the translator and proofreader learn as much as possible, a language specialist will check the changes made by the validator at the end. This ensures that all changes follow the customer’s own standards and, of course, the general rules of the language.

Would you like to discuss your organisation’s language needs? Contact us via email at contact-fi@languagewire.com for further information!

Artificial intelligence – the latest localisation superpower

22.3.2024 by Delingua

Large language models – what are they?

13.3.2024 by Sohvi Kähärä

Over the past year, it has been difficult not to come across content created by generative AI.You may have seen a LinkedIn post where OpenAI’s AI-based ChatGPT has been asked to give good tips on how to get a salary raise. Perhaps you have encountered a chatbot when you have needed help with booking an appointment online. You may have even laughed at images created by DALL·E, where the faces of familiar celebrities have been digitally added to classic works of art.

Generative AI is developing at a tremendous pace and language technology is also benefiting from these leaps of development. From the perspective of language technology, the most important role is played by large language models (LLMs).

Large language models need massive amounts of data

Generative AI solutions created for producing and processing language are called large language models. They are statistical models that calculate the probabilities of the occurrence of words or parts of words. The simplest language models calculate the probability simply by calculating how many times the word appears in the given text materials, without taking the surrounding words and their meanings into account.

Large language models, on the other hand, are advanced language models that are based on neural networks and, as their name suggests, are trained with large amounts of data. The training of the language models of previous neural machine translation engines often requires a dataset of hundreds of millions of variables but large language models require billions of them.

Current neural network-based language models, including large language models, are most often based on transformers. Transformers are neural network architectures that consist of many overlapping layers. Previous machine learning models focused on individual words in their training data, while transformers are capable of simultaneously processing and taking into account words within a sentence or a longer text and analysing, among other things, broader relationships within the sentence.

Large language models use huge text materials to learn which words appear in which context and which words often follow each other. This allows large language models to predict what words and phrases would appear in an answer suitable to a certain type of question, how a beginning of a poem could continue or how a certain matter would be expressed in another language in the context in question.

A one-size-fits-all solution is not suitable for all cases

Since the amount of data needed for training large language models is enormous, a lot of generic content will inevitably have to be used. Large language models can also be customised, or personalised, to make them more suitable for different tasks and needs. This can be done by adding additional training data in a more limited subject area and modifying the model’s weightings. It is also important to choose a suitable customisation strategy, such as building a ready-to-use model or learning through use with the aid of prompt engineering.

Especially when large language models are used for translation, it is useful to personalise language model with high-quality, fully matching bilingual materials. It is especially good if the texts used in personalisation and the new texts to be translated are from as similar subject areas as possible. For this purpose, training language models with existing translation memories is a good idea: all of the customer’s translations are saved in translation memories by language pair so these texts are always bilingual, are good matches and use the company’s desired style and terminology.

In this way, the language model learns what the customer’s texts are like and is able to imitate their style better in the future. This improves, among other things, how machine translation produced by large language models is aligned with the company’s style. This, in turn, speeds up translating as higher-quality machine translation that is customised according to the customer’s needs reduces the time involved in any post-editing required.

The downsides of AI

Although continuous learning and adaptability associated with large language models are in many respects good, they also have their downsides. Language model-based solutions in general use learn as they are running so they can also be intentionally misled and taught false information. If you repeatedly teach a language model that a pike is a bird instead of a fish, it will start believing this to be true. Large language models also suffer from so-called hallucinations, which you can read more about in our article on getting the most out of machine translation.

In addition to invented facts, another risk associated with language models trained with a large amount of data is that confidential information ends up in the wrong place. Large language models in general use are open to everyone and, when using them, it is not possible to be sure whether your data will be made available to others. Therefore, it is important to choose a reliable partner for whom data security issues are a priority.

When training large language models with translation memories, it is necessary to take care of data security and ensure that customer-specific data is used only in each customer’s own model. This way, you can avoid the situation in which the language model would introduce another customer’s confidential information into the translation. We can build a customer-specific language model directly as part of LanguageWire’s highly secure ecosystem. Read more about LanguageWire’s insights into the data security in large language models here.

Large language models as part of the future

Training large language models for translation needs is a giant leap forward as they can provide more accurate and natural translations into multiple languages. These models make it possible to produce translations quickly while taking into account the desired style and terminology. In the future, this development can break down language barriers and foster interaction between people around the world by strengthening understanding and cooperation on a global scale.