2025-10-01 –, Gaston Berger
Natural language processing (NLP) models are great at recognizing patterns, but they often fail to understand context and meaning. In this talk, I’ll show how to combine SpaCy’s NLP capabilities with knowledge-based AI (KBAI) to build smarter, context-aware models that improve accuracy and reasoning.
AI models excel at identifying language patterns, but they struggle with meaning and context. This is where knowledge-based AI (KBAI) comes in.
In this talk, I’ll demonstrate how to use SpaCy to extract structured data from text and link it to external knowledge sources (like WordNet or Neo4j). Topics include:
- Named entity recognition (NER) with SpaCy.
- Creating knowledge graphs from text data.
- Using structured knowledge to enhance model decision-making.
- Improving intent recognition and contextual accuracy.
Through live demos, I’ll show how combining pattern-based NLP with KBAI creates more accurate and context-aware AI systems.
I am a software engineer at Adobe, where I focus on product-led growth initiatives and the development of generative AI applications. Alongside, I am pursuing a Master’s degree from Georgia Institute of Technology, with a concentration in artificial intelligence, cognitive science, and human-computer interaction. My professional and academic interests lie in creating AI systems that are not only technically robust but also intuitive, explainable, and aligned with human cognitive processes. I am also a strong advocate for ethical AI, responsible technology, and diversity in the tech industry.
Through my work, research, and public speaking, I strive to advance the development of human-centered AI that is transparent, trustworthy, and accessible.