Year
Month
(Preprint) Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking
Yutao Zhu ¹, Jian-Yun Nie 聂建云 ¹, Zhicheng Dou 窦志成 ², Zhengyi Ma 马正一 ², Xinyu Zhang 张鑫宇 ³, Pan Du ¹, Xiaochen Zuo 左笑晨 ², Hao Jiang 蒋昊 ³
¹ Université de Montréal, Montréal, Québec, Canada
² Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China
中国 北京 中国人民大学高瓴人工智能学院
³ Distributed and Parallel Software Lab, Huawei, Hangzhou, Zhejiang, China
中国 浙江 杭州 华为分布式与并行软件实验室
arXiv, 2021-08-24
Abstract

Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ranking. However, a user behavior sequence has often been viewed as a definite and exact signal reflecting a user's behavior. In reality, it is highly variable: user's queries for the same intent can vary, and different documents can be clicked.

To learn a more robust representation of the user behavior sequence, we propose a method based on contrastive learning, which takes into account the possible variations in user's behavior sequences. Specifically, we propose three data augmentation strategies to generate similar variants of user behavior sequences and contrast them with other sequences. In so doing, the model is forced to be more robust regarding the possible variations. The optimized sequence representation is incorporated into document ranking.

Experiments on two real query log datasets show that our proposed model outperforms the state-of-the-art methods significantly, which demonstrates the effectiveness of our method for context-aware document ranking.
Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking_1
Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking_2
Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking_3
  • Full-dimensional complex coherence properties tomography for multi-cipher information security
  • Yonglei Liu, Siting Dai, Yimeng Zhu, Yahong Chen, Peipei Peng, Yangjian Cai, Fei Wang
  • Opto-Electronic Advances
  • 2025-03-31
  • Quantitative detection of trace nanoplastics (down to 50 nm) via surface-enhanced raman scattering based on the multiplex-feature coffee ring
  • Xinao Lin, Fengcai Lei, Xiu Liang, Yang Jiao, Xiaofei Zhao, Zhen Li, Chao Zhang, Jing Yu
  • Opto-Electronic Advances
  • 2025-03-28
  • Tunable vertical cavity microlasers based on MAPbI₃ phase change perovskite
  • Rongzi Wang, Ying Su, Hongji Fan, Chengxiang Qi, Shuang Zhang, Tun Cao
  • Opto-Electronic Advances
  • 2025-03-28
  • Light-induced enhancement of exciton transport in organic molecular crystal
  • Xiao-Ze Li, Shuting Dai, Hong-Hua Fang, Yiwen Ren, Yong Yuan, Jiawen Liu, Chenchen Zhang, Pu Wang, Fangxu Yang, Wenjing Tian, Bin Xu, Hong-Bo Sun
  • Opto-Electronic Advances
  • 2025-03-28
  • Double topological phase singularities in highly absorbing ultra-thin film structures for ultrasensitive humidity sensing
  • Xiaowen Li, Jie Sheng, Zhengji Wen, Fangyuan Li, Xiran Huang, Mingqing Zhang, Yi Zhang, Duo Cao2, Xi Shi, Feng Liu, Jiaming Hao
  • Opto-Electronic Advances
  • 2025-03-28
  • Soliton microcombs in optical microresonators with perfect spectral envelopes
  • Mulong Liu, Ziqi Wei, Haotong Zhu, Hongwei Wang, Xiao Yu, Xilin Han, Wei Zhao, Guangwei Hu, Peng Xie
  • Opto-Electronic Advances
  • 2025-03-12
  • Terahertz active multi-channel vortices with parity symmetry breaking and near/far field multiplexing based on a dielectric-liquid crystal-plasmonic metadevice
  • Yiming Wang, Fei Fan, Huijun Zhao, Yunyun Ji, Jing Liu, Shengjiang Chang
  • Opto-Electronic Advances
  • 2025-03-06
  • Spin-dependent amplitude and phase modulation with multifold interferences via single-layer diatomic all-silicon metasurfaces
  • Hui Li, Chenhui Zhao, Jie Li, Hang Xu, Wenhui Xu, Qi Tan, Chunyu Song, Yun Shen, Jianquan Yao
  • Opto-Electronic Science
  • 2025-02-19
  • Highly sensitive laser spectroscopy sensing based on a novel four-prong quartz tuning fork
  • Runqiu Wang, Shunda Qiao, Ying He, Yufei Ma
  • Opto-Electronic Advances
  • 2025-01-22
  • A novel approach towards robust construction of physical colors on lithium niobate crystal
  • Quanxin Yang, Menghan Yu, Zhixiang Chen, Siwen Ai, Ulrich Kentsch, Shengqiang Zhou, Yuechen Jia, Feng Chen, Hongliang Liu
  • Opto-Electronic Advances
  • 2025-01-22
  • Multi-photon neuron embedded bionic skin for high-precision complex texture and object reconstruction perception research
  • Hongyu Zhou, Chao Zhang, Hengchang Nong, Junjie Weng, Dongying Wang, Yang Yu, Jianfa Zhang, Chaofan Zhang, Jinran Yu, Zhaojian Zhang, Huan Chen, Zhenrong Zhang, Junbo Yang
  • Opto-Electronic Advances
  • 2025-01-22
  • Single-beam optical trap-based surface-enhanced raman scattering optofluidic molecular fingerprint spectroscopy detection system
  • Ning Sun, Yuan Gan, Yujie Wu, Xing Wang, Shen Shen, Yong Zhu, Jie Zhang
  • Opto-Electronic Advances
  • 2025-01-22



  • CMML: Contextual Modulation Meta Learning for Cold-Start Recommendation                                Intent-based policy optimization in SD-WAN
    About
    |
    Contact
    |
    Copyright © PubCard