About this Event

Hallo Münchners,

We would like to invite you to our October meetup with two exciting talks at a very cool location, for which we want to thank Alasco for hosting us this evening & sponsoring the refreshments.

This event is brought to you in collaboration with the MunichNLP community. Join their Discord to discuss the latest developments and also stimulate exchange on research and innovation around NLP. Hurry up we have limited spots and see you on the other side.

Agenda

• 6:30pm Door opening, pizza arrives, drinks, casual welcoming
• 7:00pm Quick Introduction - 3min (MunichNLP) + 2 mins welcome words from Alasco
• 7:05pm Lanfrica: Tackling the deep-rooted AI challenges in the Global majority + Q&A by Chris Emezue
• 7:50 pm Break
• 8:00pm Approaches to Question Answering in Network Engineering + Q&A by Dr. Oliver Pfaffel
• 8:30pm Break
• 9:00pm Food and Drinks + Networking
• 9:55pm Event conclusion

Speaker

Chris Emezue is a seasoned researcher committed to developing intelligent systems that can learn even in low-resource scenarios, and are reliable. His research areas are natural language processing, causality, and reinforcement learning. As a dedicated contributor to the field of AfricaNLP, he has worked on several key projects to improve the representation of low-resource African language technologies and datasets. Furthermore, as an entrepreneur, Chris is building Lanfrica, a startup that aims to accelerate the development of AI applications in under-represented regions.

Dr. Oliver Pfaffel has been working as a data scientist / NLP engineer in insurance for more than a decade. He holds a PhD in mathematical statistics (TUM, Columbia, NUS) and regularly lectures at the European Actuarial Academy and TUM. In this introductory talk, we delve into various strategies employed for question answering tailored specifically to the field of network engineering. We will cover generative solutions using large language models as well as retrieval-based techniques, which we will demonstrate using a sample StackExchange dataset. Considerations will be given to the use of private or confidential data. We will critically analyze different evaluation types, elaborating on their respective advantages and limitations. It is important to note that this presentation is grounded in a personal project and holds no affiliation to any professional activity or company.