Search Articles

View query in Help articles search

Search Results (1 to 9 of 9 Results)

Download search results: CSV END BibTex RIS


A Method to Learn Embedding of a Probabilistic Medical Knowledge Graph: Algorithm Development

A Method to Learn Embedding of a Probabilistic Medical Knowledge Graph: Algorithm Development

The number of relations was so small that it was possible to train the embedding of all entities and relations in the same space to satisfy the training objective, which was similar to the result that the link prediction performance of Trans H was worse than Trans E on the WN18 data set used by Wang et al [6]. The results of Trans E and Pr Trans E were quite similar under the Hits@10 and NDCG@10. In particular, the NDCG@10 of Trans E was slightly better than that of Pr Trans E.

Linfeng Li, Peng Wang, Yao Wang, Shenghui Wang, Jun Yan, Jinpeng Jiang, Buzhou Tang, Chengliang Wang, Yuting Liu

JMIR Med Inform 2020;8(5):e17645