The emergence of “large language models” such as ChatGPT in 2022 is a logical consequence and further development of neural machine translation, which has been part of everyday translator life since 2017. Instead of using bilingual data sets, usually TMX files, these “large language models” are trained with vast amounts of data of all kinds in order to solve a wide variety of tasks.

In addition to texts, translations and image generation, this also includes programming.Instead of letting LLMs such as ChatGPT process tasks themselves via prompts (subject of the prompting training on March 19/20, 2025), the LLM can be asked to create a script for this task. This can then be used to perform recurring and less exciting routine tasks, but also to reliably manipulate large data sets such as TMX files. In this case, the LLM does not act as a translator or terminologist, but as a developer who is always available.

To do this, it is necessary to be able to describe exactly what the task is to the machine developer via prompting and to be able to test the result, the code, in the programming language used and ask for improvements until the result is satisfactory.

As with learning any language, this requires a basic understanding of the vocabulary and syntax of programming languages. Python is used as the programming language in the training. It was developed specifically for the training of programmers and is therefore easier to learn than other programming languages. Secondly, Python is the language that is relevant in the AI environment, i.e. in the environment that becomes relevant for translators and terminologists.

The training will use examples from the field of translation and terminology, so we will mainly work with words and will not delve deeper into mathematical issues.

This workshop is aimed at absolute beginners in the field of programming. In order to keep the group organization homogeneous, we ask all those who already know other programming languages or already have initial programming experience to refrain from participating.

Content of the training

• Create comments
• Working with functions: print() and input()
• Using variables, lists and dictionaries
• Use loops to repeat activities
• Create conditions
• Open, read, write and close files
• Outlook: Python and databases, neural networks

The theoretical parts are always followed by a workshop part with interactive exercises in which the participants can put what they have learned into practice.

A laptop, camera and sound are required to participate in the training. You need access to ChatGPT. All you need to do is register without incurring any additional costs. The Thonny development environment used does not require much memory on your computer and is easy to install.

You are welcome to use your own texts for the interactive translation and terminology exercises, but these test texts must be published or uploaded to cloud providers.Otherwise, we recommend that you use the Pro versions.You will receive further information after registration.

The training is divided into 3 dates and takes place from 09:30 – 13:00 on the following dates:
Tuesday, 01.07.2025
Wednesday, 02.07.2025
Thursday, 03.07.2025

The key to the long-term success of a terminology project is systematic terminology coordination – in the terminology circle.

In this webinar, you will learn what needs to be considered when setting up a terminology group, who should be involved and how to make the coordination process as efficient as possible.

Contents:

Coordination processes and practical work in the terminology group

Structure, types and uses of terminology circles

Tasks of the terminology officer

You can’t do it without rules: the basis for standardizing terminology is the guideline. In this webinar, you will find out what needs to be included. (german language)
Using examples, we work out how to set up a terminology guideline and what makes a good term.

Contents:

• Structure and use of a terminology guideline
• Criteria for evaluating designations
• Introduction to naming
• Systematic development of company-specific rules

Terminology work is not only indispensable for terminologists, but also for editors and translators. But how can I quickly obtain an initial inventory and how can I expand it?

At the beginning of the webinar, a distinction is made between manual, semi-automatic and automatic terminology extraction.Various commercial and open source extraction tools are presented and the advantages and disadvantages of their use are explained.

What can be extracted?What is really important and should be included in the database?

The webinar will also cover the various data categories in a terminology database – and the terminology research phase, as this forms the basis of terminology extraction.

Since ChatGPT, artificial intelligence has become part of everyday life and work. Translators have been familiar with AI for some time – through the post-editing of machine-generated texts. However, terminology in particular is neglected in these systems. This results in new requirements, but above all many new perspectives for the translation profession.

This webinar will show how neural machine translation systems, GPTs and large language models work and how terminology can be influenced in automatic text creation and translation.

With the advent of machine translation – whether neural or with the help of large language models – the translator’s task is shifting from translating texts to quality management of pre-translated texts and, above all, to multilingual terminology work even before translation. After all, who knows more about terms and their terminology than specialist translators?

However, having high-quality terminology in foreign languages recorded in a termbase is still something new for many customers. Until now, they have tended to see terminology as a “by-product” that is created with every translation job and is included in the translation memories. With translations created by AI, this no longer works – and so terminology work is becoming a mandatory basis for machine-translated texts.

For many translators, setting up multilingual terminology, integrating it into the training and translation phase and monitoring it in the quality assurance process is a new and challenging task – but one that can be a lot of fun!

The training provides the necessary knowledge about the current requirements for multilingual terminology work in times of AI, about methods and their implementation in various tools. 1.5 hours of theory is followed by a workshop section with interactive exercises in which participants can also reflect on and evaluate their own experiences with tools and terminology projects.

Contents theory part – 09:30 am to 11:00 am

• Fundamentals of terminology and terminology work: principles and concepts, e.g. permitted and prohibited terms, classification of terms (synonyms, homonyms)
• Requirements for the development of multilingual terminology
• Systematic vs. ad hoc terminology work vs. terminology work during translation
• Terminology databases in comparison: with two levels or three levels, term-oriented or naming-oriented, naming-autonomous vs. static, with free vs. fixed data categories, etc.
• Requirements for definitions and dealing with sources

Content practical part – 11:30 am to 1:00 pm

Joint development of terminology in various systems available online. For the interactive part, please let us know in advance which tools are to be included in the analysis. We recommend a laptop with headset and camera for participation in the group work.

The requirements for terminology management and reconciliation systems in companies are increasing. Termbases must be easy to use and self-explanatory for inexperienced users from all departments and around the world, while at the same time meeting all interface requirements with and without AI. This is why the requirements for the design of termbases are becoming increasingly complex.

At the same time, customers and their systems provide Excel lists, glossaries or bilingual dictionaries as input, which first have to be adapted to the requirements of modern terminology management before they can be adopted. Terminology management systems are therefore just as challenging as maintaining other systems in the company, such as a content management system.

The training provides you with the necessary knowledge about the current requirements for the design of multilingual terminology databases. 1.5 hours of theory will be followed by a workshop section in which participants will be able to implement various concepts in online databases and reflect on and evaluate their own experiences with the conception of termbases.

Contents theory part – 09:30 am to 11:00 am

• Conceptual orientation and naming autonomy
• Design data categories and define structure
• One or more databases? – Advantages and disadvantages
• Basic considerations for assigning rights
• Design release processes
• Revision of terminology databases

Content practical part – 11:30 am to 1:00 pm

• Implementation of various concepts in different systems available online. For the interactive part, please let us know in advance which tools are to be included in the analysis. We recommend a laptop with headset and camera for participation in the group work.

Few systems in a company are as complex as a terminology management system, which has to meet all the requirements of knowledge management in the company, the knowledge of terms, their definitions and their designations.

This is why most systems support a completely free termbase design and company-specific data categories. However, due to its complexity, this also requires some fundamental thought about how this terminological data can be exchanged with or integrated into other systems.

The training provides the necessary knowledge about current exchange formats and tools that can facilitate the conversion. 1.5 hours of theory is followed by a workshop section in which participants can compare different exchange formats and convert them into other formats.

Contents theory part – 09:30 am to 11:00 am

• From glossary to termbase – from termbase to glossary: integration into AI systems
• csv, Excel or tbx – how would the connected system like it?
• Operating interfaces and APIs
• Presentation of tools for conversion

Content practical part – 11:30 am to 1:00 pm

• Comparison of different formats and different tbx dialects and possibilities for their conversion. For the interactive part, please let us know in advance which tools and formats are to be included in the analysis. We recommend a laptop with headset and camera for participation in the group work.