Company Filing History:
Years Active: 2025
Title: Nadja Herger: Innovator in AI Explainability
Introduction
Nadja Herger is a prominent inventor based in Thalwil, Switzerland. She has made significant contributions to the field of artificial intelligence, particularly in the area of explainability. Her work focuses on developing methods and systems that enhance the understanding of AI model outputs.
Latest Patents
Nadja holds 1 patent for her invention titled "Systems and methods for analysis explainability." This patent describes methods and systems for providing mechanisms to present artificial intelligence (AI) explainability metrics associated with model-based results. In her invention, a model is applied to a source document to generate a summary. An attention score is determined for each token of a plurality of tokens in the source document, indicating the relevance of each token to the model-based summary. The tokens are aligned to at least one word in the source document, and the attention scores are combined to generate an overall attention score for each word. This innovative approach allows for the display of words with an indication of their overall attention scores, enhancing the interpretability of AI models.
Career Highlights
Nadja is currently employed at Thomson Reuters Enterprise Centre GmbH, where she continues to push the boundaries of AI technology. Her work is instrumental in bridging the gap between complex AI models and user understanding.
Collaborations
Nadja collaborates with talented professionals such as Nina Hristozova and Milda Norkute, contributing to a dynamic and innovative work environment.
Conclusion
Nadja Herger's contributions to AI explainability are paving the way for more transparent and understandable artificial intelligence systems. Her innovative patent and ongoing work at Thomson Reuters Enterprise Centre GmbH highlight her commitment to advancing technology in meaningful ways.