Skip to main content

Table 2 Additional features for diversity-biased learning-to-rank model.

From: Learning to rank diversified results for biomedical information retrieval from multiple features

Feature Description
#RelAsp Number of relevant aspects the passage contains.
#NonRelAsp Number of irrelevant aspects the passage contains.
#NewRelAsp Number of new relevant aspects the passage contains compared with afore ranked passages.
#OldRelAsp Number of relevant aspects that already existed in afore ranked passages.
NewAspPsg Ratio of passages that contains new aspects with all afore ranked passages.
%RelAsp Ratio of number of relevant aspects with all aspects before current rank position.
%UniqRelAsp Ratio of unique relevant aspects with all aspects before current rank position.