Tracing the Flow of Knowledge From Science to Technology Using Deep Learning
To register for this seminar with Eventbrite please click here
Abstract:
We identify a similarity model suitable for working with patents and scientific publications at the same time. In a horse race-style evaluation, we subject eight language (similarity) models to prediction credible Patent-Paper Citations. We find that our Pat-SPECTER model performs best, which the SPECTER2 model fine-tuned on patents. In two real-world scenarios (separating patent-paper-pairs and predicting patent-paper-pairs) we demonstrate the capabilities of the Pat-SPECTER. Using the model, we finally study which patent characteristics (authorities, CPC classes) predict references to related scientific literature. The model is open for the academic community and practitioners alike.
Bio:
Michael E. Rose is a senior research fellow at the Max Planck Institute for Innovation and Competition. He holds a PhD in Economics from the University of Cape Town. His research interests include Economics of Science, Technology Transfer (both in historic and contemporaneous perspective), and Digital Transformation.
Link: https://michael-e-rose.github.io/