Reranking rearranges items in the initial rankinglists from the previous ranking stage to better meet users’ demands . An ideal reranking algorithm should consider the counterfactual context — the position and the alignment of the items in reranked lists . CRUM significantly outperforms the state-of-the-art models in terms of both relevance-based metrics and utility-based metric metrics. CRUM outperforms other models in both relevance based on utility and relevance based metrics, according to the authors of this article . The authors propose a novel pairwise reranking framework, CRUM, which maximizes theoverall utility after reranking efficiently. It is based on a real-world dataset and a proprietary real world data set that was created by the author of the author’s research. For more information, visit the author’s blog

Author(s) : Yunjia Xi, Weiwen Liu, Xinyi Dai, Ruiming Tang, Weinan Zhang, Qing Liu, Xiuqiang He, Yong Yu

Links : PDF - Abstract

Code :
Coursera

Keywords : based - reranking - utility - relevance - metrics -

Leave a Reply

Your email address will not be published. Required fields are marked *