论文信息 - Predicting Relevance based on Assessor Disagreement

Predicting Relevance based on Assessor Disagreement

We present the Predicted Relevance Model (PRM): it allows moving from binary evaluation measures that reﬂect a single assessor’s judgments, towards graded measures that represent the relevance towards random users.

Chris Develder | D. Hiemstra | R. Aly | T. Demeester | Dong Nguyen

[1] Djoerd Hiemstra,et al. Predicting relevance based on assessor disagreement: analysis and practical applications for search evaluation , 2015, Information Retrieval Journal.