Search task success evaluation by exploiting multi-view active semi-supervised learning

作者:

Highlights:

• Propose MA4SE that exploits labeled data and unlabeled data by integrating the advantages of both semi-supervised learning and active learning with the multi-view mechanism.

• Design an integrated selection strategy to measure the informativeness and the representativeness of contention search tasks.

• Conduct extensive experiments on open datasets to show that the proposed approach outperforms the state-of-the-art semi-supervised search task success evaluation approach.

摘要

•Propose MA4SE that exploits labeled data and unlabeled data by integrating the advantages of both semi-supervised learning and active learning with the multi-view mechanism.•Design an integrated selection strategy to measure the informativeness and the representativeness of contention search tasks.•Conduct extensive experiments on open datasets to show that the proposed approach outperforms the state-of-the-art semi-supervised search task success evaluation approach.

论文关键词:Search task success evaluation,Semi-supervised learning,Active learning,Multi-view mechanism

论文评审过程:Received 7 August 2019, Revised 4 November 2019, Accepted 5 December 2019, Available online 10 December 2019, Version of Record 10 December 2019.

论文官网地址:https://doi.org/10.1016/j.ipm.2019.102180