%0 Conference Proceedings %T Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings %A Chang, David %A Balažević, Ivana %A Allen, Carl %A Chawla, Daniel %A Brandt, Cynthia %A Taylor, Andrew %Y Demner-Fushman, Dina %Y Cohen, Kevin Bretonnel %Y Ananiadou, Sophia %Y Tsujii, Junichi %S Proceedings of the 19th SIGBioMed Workshop on Biomedical Language Processing %D 2020 %8 July %I Association for Computational Linguistics %C Online %F chang-etal-2020-benchmark %X Much of biomedical and healthcare data is encoded in discrete, symbolic form such as text and medical codes. There is a wealth of expert-curated biomedical domain knowledge stored in knowledge bases and ontologies, but the lack of reliable methods for learning knowledge representation has limited their usefulness in machine learning applications. While text-based representation learning has significantly improved in recent years through advances in natural language processing, attempts to learn biomedical concept embeddings so far have been lacking. A recent family of models called knowledge graph embeddings have shown promising results on general domain knowledge graphs, and we explore their capabilities in the biomedical domain. We train several state-of-the-art knowledge graph embedding models on the SNOMED-CT knowledge graph, provide a benchmark with comparison to existing methods and in-depth discussion on best practices, and make a case for the importance of leveraging the multi-relational nature of knowledge graphs for learning biomedical knowledge representation. The embeddings, code, and materials will be made available to the community. %R 10.18653/v1/2020.bionlp-1.18 %U https://aclanthology.org/2020.bionlp-1.18 %U https://doi.org/10.18653/v1/2020.bionlp-1.18 %P 167-176