Relevance estimation is one of the core concerns of information retrieval (IR) studies.Although existing retrieval models gained much success in both deepening our under-standing of information seeking behavior and building effec-tive retrieval systems,we have to admit that the models work in a rather different manner from how humans make relevance judgments.Users' information seeking behaviors involve com-plex cognitive processes,however,the majority of these behav-ior patterns are not considered in existing retrieval models.To bridge the gap between practical user behavior and retrieval model,it is essential to systematically investigate user cogni-tive behavior during relevance judgement and incorporate these heuristics into retrieval models.In this paper,we aim to for-mally define a set of basic user reading heuristics during rel-evance judgement and investigate their corresponding model-ing strategies in retrieval models.Further experiments are con-ducted to evaluate the effectiveness of different reading heuris-tics for improving ranking performance.Based on a large-scale Web search dataset,we find that most reading heuristics can im-prove the performance of retrieval model and establish guide-lines for improving the design of retrieval models with human-inspired heuristics.Our study sheds light on building retrieval model from the perspective of cognitive behavior.

Xiangsheng LI;Yiqun LIU;Jiaxin MAO

Department of Computer Science and Technology,Institute for Artificial Intelligence,Beijing National Research Center for Information Science and Technology,Tsinghua University,Beijing 100084,China

计算机科学前沿

[1]Xiangsheng LI;Yiqun LIU;Jiaxin MAO-.Understanding the role of human-inspired heuristics for retrieval models)[J].计算机科学前沿,2022(01):10-20

heuris

Understanding,role,inspired,heuristics,retrieval,models,Relevance,estimation,one,core,concerns,information,studies,Although,existing,gained,much,success,both,deepening,our,under,seeking,building,systems,have,admit,that,work,rather,different,manner,from,humans,make,relevance,judgments,Users,behaviors,involve,com,plex,cognitive,processes,however,majority,these,patterns,are,not,considered,To,bridge,gap,between,practical,user,essential,systematically,investigate,during,judgement,incorporate,into,In,this,paper,aim,mally,define,basic,reading,their,corresponding,strategies,Further,experiments,ducted,evaluate,effectiveness,improving,ranking,performance,Based,large,scale,search,dataset,find,most,can,prove,establish,guide,lines,design,Our,study,sheds,light,perspective

0.506206