Key points are not available for this paper at this time.
Patent references to science provide a valuable paper trail for investigating the knowledge flow from science to technological innovation. Research on patent–paper links has mostly concentrated on front-page references, often neglecting the more complex in-text references. Therefore, we developed a three-stage machine-learning pipeline to extract and match patent in-text references to scientific publications. Our pipeline performs the following tasks: (1) extracting reference strings from patent texts, (2) parsing fields from these reference strings, and (3) matching references to publications in the Web of Science (WoS) database. We developed a training dataset consisting of 3,900 (and 3,901) manually annotated references from 392 (and 319) randomly selected EPO (and USPTO) patents. The first stage, reference extraction, achieved almost perfect results with a precision of 98.9% and a recall of 97.7% at the reference level. Overall, the pipeline demonstrated robust performance, with a precision of 96.8% and a recall of 91.9% at the unique patent-paper-pair level. Applying this pipeline to EPO and USPTO patents granted between 1990 and 2022, we identified 5,438,836 (and 20,432,189) references from 492,469 (and 1,449,398) EPO (and USPTO) patents, 2,763,779 (and 11,069,995) of which are matched to WoS publications. This extensive dataset is a valuable resource for studying science-technology linkages. We offer open access to this dataset, along with the associated code and training data. • High-performing ML pipeline extracts and matches patent in-text references. • Achieves 96.8% precision and 91.9% recall at patent-paper-pair level. • Dataset links EPO & USPTO patent in-text references to Web of Science papers. • A high-quality, manually annotated dataset supports patent text analysis.
Abbasiantaeb et al. (Wed,) studied this question.