NLP à la Suisse by Andrea Mocci and Jesper Findahl

Explore the complexities of Natural Language Processing (NLP) in a multilingual context through this 45-minute conference talk from Devoxx. Dive into the challenges of processing human language data, particularly in a country like Switzerland with four official languages. Learn about the components of a modern NLP pipeline, from basic tasks such as tokenization and lemmatization to advanced techniques including Named Entity Recognition (NER), coreference resolution, and dependency parsing. Discover how Large Language Models (LLMs) like GPT can be integrated to potentially enhance NLP pipelines. Gain insights from a real-world application using the Swiss Commercial Registry, a complex multilingual public database, as part of an interdisciplinary research project in economics and political science. Understand how cutting-edge NLP technology is being utilized to build the software engineering backbone for this expansive project.

NLP à la Suisse by Andrea Mocci and Jesper Findahl