Tracing the Flow of Knowledge From Science to Technology Using Deep Learning
This work addresses the need for better tools to analyze knowledge transfer from science to technology, particularly for researchers and practitioners in patent analysis, though it is incremental as it fine-tunes an existing model.
The authors tackled the problem of tracing knowledge flow between patents and scientific papers by developing a language similarity model, Pat-SPECTER, which outperformed other models in predicting credible citations and demonstrated utility in real-world scenarios.
We develop a language 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 predict credible Patent-Paper Citations. We find that our Pat-SPECTER model performs best, which is 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. We finally test the hypothesis that US patents cite papers that are semantically less similar than in other large jurisdictions, which we posit is because of the duty of candor. The model is open for the academic community and practitioners alike.