Module 1: Computer-Aided Translation and Basic Programming
Introduction to Python Programming (every day of the 1st module)
In the first module, participants learn how to automate everyday translation work using programs they create themselves. The basis for this is an introduction to the Python programming language. With the help of practical exercises in class and voluntary homework, participants will learn in particular how large files - for example translation memories - can be adapted to their own needs. No previous knowledge of programming is required.
Course day 1: Latest Developments in CAT Tools
On this course day, the most important new functionalities in common CAT tools will be presented. Special attention will be paid to functionalities that are directly related to the use of MT when working in the CAT tool: Which MT systems can be integrated into CAT tools? How can MT proposals and CAT-Tools hits be combined and used productively? What tools do CAT tools offer in terms of quality of MT and post-editing effort? Participants will have the opportunity to apply what they have learned in practical exercises.
Course day 2: Style and Quality Checking; Project Management
This course day deals with automated workflows on the topics of style and quality checking. Style and Quality Checking affect not only the target text that is being created, but especially the Translation Memory (TM) in which it is stored. Participants will learn basic methods and criteria of Style and Quality Checking. Further topics of this course day are the handling of common free and CAT tool-bound tools as well as automated TM maintenance (among others with the help of the regular expressions learned in the previous course day).
Course day 3: File Formats and Encoding; Query Languages and Regular Expressions
On this course day, the most important file formats for processing and exchanging linguistic data will be presented. Furthermore, relevant query languages for querying and processing information from data sources will be presented. Another focus is the use of so-called regular expressions for filtering and processing relevant data in large data sets based on certain patterns and criteria.
Course day 4: Term Databases and Term-Extraction
First of all, the basic concepts of terminology are explained. Building on this foundation, participants will then learn about different methods and tools that can be used to extract terminology from texts and text collections. Further topics are basic properties of terminology databases and their components, as well as established methods with regard to the construction of terminology databases. Following the theoretical inputs, the participants will consolidate their knowledge by means of short practical exercises.
Course day 5: Audiviosual Translation (AVT)
This course day addresses Audiovisual Translation, with a particular focus on the theory and practice of subtitling. The session starts with an overview of this rich and varied discipline before moving on to cover the basics of both the linguistic and technical aspects of subtitling. Participants will learn through a combination of theoretical examples and hands-on tasks. Other sessions will discuss automation and machine learning in the subtitling context, and provide an overview of training and working opportunities within the industry. Access to film material and software will be provided.
Module 2: Machine Translation and AI
Course day 6: Introduction to Artificial Intelligence: Machine Learning and Neural Networks
The course day teaches basics in machine learning, especially with artificial neural networks.
Simple examples are used to show how artificial neural networks are constructed and how they can be used to learn various applications if suitable training material exists. Focusing on natural language processing, the course addresses how words and sentences can be represented in neural networks, and what impact the type of representation has on machine learning. Fundamental concepts such as embeddings and recurrent networks will be introduced.
Course day 7: Neural Machine Translation: Technology, Applications and Limits
Machine translation has made remarkable progress in recent years due to improvements in neural modeling. We explain the technical background without going into mathematical details: How do we use neural networks to automatically translate texts from one language to another? We describe various use cases, ranging from fully automatic translation for assimilation to incorporation into workflows for professional translation. We discuss the integration of company-specific terminology and the adaptability of machine translation to country-specific variants. In light of claims about human-machine parity, we also discuss the limitations of the technology and future directions in machine translation research.
Course day 8: Post-Editing Techniques: Scenarios and Experiences
In this course block, the focus is on the post-editing of automatically translated texts. We will discuss the role that post-editing plays in the translator's field of work, how it influences it, and look at different scenarios in which post-editing can be used. We will also discuss how post-editing differs from editing human translations and for which types of texts it is particularly suitable. We will also look at how post-editing is done, how it can be done efficiently, and how post-editing can be integrated into work with other tools. The theoretical knowledge will be applied in practical exercises adapted to different language versions.
Course day 9: Translation Technology and AI for Accessibility: Simplified Language, Sign Language
This course day aims to introduce participants to the use of machine translation as an assistive technology in two areas: automatic text simplification and automatic translation from/to sign language. The day will start with a theoretical introduction to the concepts of easy language and sign language, followed by an overview of experimental linguistics studies for a better understanding of the needs of target groups (e.g., reception studies to test the applicability of different recommendations for producing easy language).
The second half of the day will be devoted to the state of the art of computer-assisted translation and fully automatic translation in the context of easy language and sign language. Particular attention will be paid to identifying the AI content of these technologies, highlighting their limitations, and working together to identify meaningful areas of application.
Course day 10: Spoken Language Processing: Speech Recognition, Speaker Recognition, and Automatic Interpreting
Spoken language is playing an increasingly important role in automatic translation. We will first address which information in a speech signal can basically be processed automatically. Basic steps necessary for the automatic processing of spoken language and the associated problems will then be illustrated with simple examples and visualized with different programs. The theoretical basics acquired in this way serve to better assess the plausibility and expected success of various practical applications.
In the second half of the course day, important application areas of automatic processing of spoken language will be covered. These include speech recognition (automatic transcription of the speech signal), speech synthesis (automatic generation of spoken language), and voice recognition (automatic recognition of the speaker), as well as more specific methods for automatic translation such as 'respeaking' or automatic interpreting.
Course day 11: Soft Factors: Ergonomics, Risk and Change Management, Ethical and Legal Aspects
This course block aims to contribute to the empowerment of professional translators in their role as Reflective Practitioners in dealing with language technology. We address the personal and organizational opportunities and risks that using complex translation systems can bring. This includes considerations of ethical and legal aspects such as professional ethics and data protection. It also includes considerations of what it takes to successfully implement and use such support tools for all concerned. We also look at what it takes for professional translators who provide post-editing to be able to deal with the high cognitive load of this activity in an ergonomically sound way. On all topics, course participants learn about findings from applied (translation) research on the one hand and contribute their personal experiences and ideas on the other.