Globalization and Localization

The rapid evolution of technology in large language models (LLMs) has presented unparalleled prospects and challenges in the realm of translation. Given the voluminous technical documents and complex version control, a translation management platform is crucial for enhancing translation efficiency. The presentation will start with a case study on the successful use of the YiCAT online translation management platform in technical translation. Next, the speech will introduce the application of LLMs in translating technical documents. Applications include ChatGPT-based translation, terminology intervention, enhanced translation integrating translation memories and terminology databases, automatic polishing, as well as automatic post-editing. The speech will share the latest exploration of using large LLMs in technical translation, including fine-tuning practices using open-source LLMs and ChatGPT, terminology extraction based on LLMs, and automatic machine translation quality estimation. In conclusion, the speaker will focus on the outlook for the extensive integration of LLMs technology with translation applications by 2024. It is expected that translators may fully understand and effectively utilize LLMs, thereby improving the efficiency of translating technical documents.

With enterprises in China rapidly progressing towards globalization, their demand for efficient publishing of multilingual content are increasingly growing. In this process, quality management becomes much more important. This talk will explore how to effectively establish style guidelines for multilingual content, enabling efficient terminology management and real-time monitoring of document quality. It will also explore methods for evaluating the translation quality of vendors. Whether you are a manual engineer, a localization project manager or a multilingual translator, this sharing will provide you with practical strategies, tools and best practices for managing the quality of multilingual content.

Does the following sound familiar to you?

Your team applies terminology lists, which do not (entirely) comply with the terminology lists of other teams in your company. Your company’s terminology is inconsistent for team colleagues and customers alike. All this leads to unnecessary confusion and miscommunication.

Then let us take you with us on our terminology race!

In this presentation, we, Porsche project lead Ira Rotzler and Kerstin Berns, managing partner of berns language consulting will share with you, why and now we started the Porsche terminology race, where we stand right now, and how we plan to cross the finishing line 😊!

We will demonstrate to you how we unified a great number of very differently formatted terminology lists into one neat data set and how we cleaned up all that data. We will also share with you how we managed to lay the foundation for high-quality terminology management which is useful to the entire Porsche brand in all countries, worldwide! And of course, we will shed light on how we automated this process and which methodologies and tools where applied.

In the end, we will talk about how the project team successfully created a reliable and useful database that benefits Porsche in various ways, e.g., by improving recognition of vehicle functions and their understandability throughout different customer touchpoints.

Finally, we take a sneak peek into the international future of multilingual terminology work at Porsche as well as at the future usefulness of clean terminology for simply everything!