A Simple yet Effective Framework for Active Learning to Rank
作者机构：Baidu IncorporatedBeijing 100085China
出 版 物：《Machine Intelligence Research》 (机器智能研究（英文版）)
年 卷 期：2024年第21卷第1期
页 面：169-183页
核心收录：
学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：This work was supported in part by the National Key R&D Program of China(No.2021ZD0110303)
主 题：Search information retrieval learning to rank active learning query by committee
摘 要：While China has become the largest online market in the world with approximately 1 billion internet users,Baidu runs the world s largest Chinese search engine serving more than hundreds of millions of daily active users and responding to billions of queries per *** handle the diverse query requests from users at the web-scale,Baidu has made tremendous efforts in understanding users queries,retrieving relevant content from a pool of trillions of webpages,and ranking the most relevant webpages on the top of the *** the components used in Baidu search,learning to rank(LTR)plays a critical role and we need to timely label an extremely large number of queries together with relevant webpages to train and update the online LTR *** reduce the costs and time con-sumption of query/webpage labelling,we study the problem of active learning to rank(active LTR)that selects unlabeled queries for an-notation and training in this ***,we first investigate the criterion-Ranking entropy(RE)characterizing the entropy of relevant webpages under a query produced by a sequence of online LTR models updated by different checkpoints,using a query-by-com-mittee(QBC)***,we explore a new criterion namely prediction variances(PV)that measures the variance of prediction res-ults for all relevant webpages under a *** empirical studies find that RE may favor low-frequency queries from the pool for la-belling while PV prioritizes high-frequency queries ***,we combine these two complementary criteria as the sample selection strategies for active *** experiments with comparisons to baseline algorithms show that the proposed approach could train LTR models to achieve higher discounted cumulative gain(i.e.,the relative improvement DCG4=1.38%)with the same budgeted labellingefforts.
维普期刊数据库