A bias–variance evaluation framework for information retrieval systems

作者：

Highlights：

• A unified bias–variance metric evaluates retrieval effectiveness–stability tradeoff.

• A generalized bias–variance metric is defined based on across topic and per-topic.

• Studying the factors that influence the bias–variance metric (topic grouping, etc.).

• Decomposition of a variance can effectively track the source of system instability.

摘要

•A unified bias–variance metric evaluates retrieval effectiveness–stability tradeoff.•A generalized bias–variance metric is defined based on across topic and per-topic.•Studying the factors that influence the bias–variance metric (topic grouping, etc.).•Decomposition of a variance can effectively track the source of system instability.

论文关键词：Information retrieval,Evaluation metrics,Effectiveness–stability tradeoff

论文评审过程：Received 25 January 2021, Revised 6 August 2021, Accepted 30 August 2021, Available online 6 October 2021, Version of Record 6 October 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102747