Research results manifest in large corpora of patents and scientific papers. However, both corpora lack a consistent taxonomy and references across different document types are sparse. Therefore, and because of contrastive, domain-specific language, recommending similar papers for a given patent (or vice versa) is challenging. We propose a recommender system that leverages topic distributions and keywords to recommend related work despite these challenges. As a case study, we evaluate our approach on patents and papers of two fields: medical and computer science. We find that topic-based recommenders complement word-based recommenders for documents with collectionspecific language and increase mean average precision by up to 27%. As a result of our work, publications from both corpora form a joint digital library, which connects academia and industry.