Ralf Krestel (HPI), Renukswamy Chikkamath (Uni Passau), Christoph Hewel (BETTEN und RESCH Patent- und Rechtsanwaelte PartGmbB), and Julian Risch (HPI) compiled a survey paper on deep learning methods applied in the patent domain. The article can be accessed free of charge for the next couple of weeks: https://authors.elsevier.com/a/1cqCJ_3wd9MsOn
Patent document collections are an immense source of knowledge for research andinnovation communities worldwide. The rapid growth of the number of patent documents poses an enormous challenge for retrieving and analyzing information from this source in an effective manner. Based on deep learning methods fornatural language processing, novel approaches have been developed in the field of patent analysis. The goal of these approaches is to reduce costs by automating tasks that previously only domain experts could solve. In this article, we provide a comprehensive survey of the application of deep learning for patent analysis.We summarize the state-of-the-art techniques and describe how they are applied to various tasks in the patent domain. In a detailed discussion, we categorize 40 papers based on the dataset, the representation, and the deep learning architecturethat were used, as well as the patent analysis task that was targeted. With oursurvey, we aim to foster future research at the intersection of patent analysis anddeep learning and we conclude by listing promising paths for future work.