pbio.2005343.g001.tif (1.59 MB)
The overall architecture of the new relevance search algorithm in PubMed.
figure
posted on 2018-08-28, 17:26 authored by Nicolas Fiorini, Kathi Canese, Grisha Starchenko, Evgeny Kireev, Won Kim, Vadim Miller, Maxim Osipov, Michael Kholodov, Rafis Ismagilov, Sunil Mohan, James Ostell, Zhiyong Lu(a) It consists of two stages: processing first by BM25, a classic term-weighting algorithm; the top 500 results are then re-ranked by LambdaMART, a high-performance L2R algorithm. The machine-learning–based ranking model is learned offline using relevance-ranked training data together with a set of features extracted from queries, documents, or both. (b) Features designed and experimented in this study with their brief descriptions and identifiers. D, document; IDF, inverse document frequency; L2R, learning to rank; Q, query; QD, query–document relationship; TIAB, title and abstract
