Our submission “What Should I Cite? Cross-Collection Reference Recommendation for Patents and Papers” by Julian Risch and Ralf Krestel has won the Best Short Paper/Poster/Demo Award at the 21st International Conference on Theory and Practice of Digital Libraries (TPDL 2017). The award was received on September 20, 2017 in Thessaloniki. We are very proud of this prestigious award and the recognition it represents. The paper can be found here.
Abstract
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 hybrid recommender system that leverages topic distributions and key terms 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 term-based recommenders for documents with collection-specific language and increase mean average precision by up to 23%. As a result of our work, publications from both corpora form a joint digital library, which connects academia and industry.
