DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval

@article{Pang2017DeepRankAN,
  title={DeepRank: A New Deep Architecture for Relevance Ranking in Information Retrieval},
  author={Liang Pang and Yanyan Lan and Jiafeng Guo and Jun Xu and Jingfang Xu and Xueqi Cheng},
  journal={ArXiv},
  year={2017},
  volume={abs/1710.05649}
}
  • Liang Pang, Yanyan Lan, +3 authors Xueqi Cheng
  • Published in CIKM '17 2017
  • Computer Science
  • ArXiv
  • This paper concerns a deep learning approach to relevance ranking in information retrieval (IR. [...] Key Method Firstly, a detection strategy is designed to extract the relevant contexts. Then, a measure network is applied to determine the local relevances by utilizing a convolutional neural network (CNN) or two-dimensional gated recurrent units (2D-GRU). Finally, an aggregation network with sequential integration and term gating mechanism is used to produce a global relevance score. DeepRank well captures…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 64 CITATIONS, ESTIMATED 94% COVERAGE

    Deep Neural Network Regularization for Feature Selection in Learning-to-Rank

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Modeling Diverse Relevance Patterns in Ad-hoc Retrieval

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS

    A Deep Look into Neural Ranking Models for Information Retrieval

    VIEW 11 EXCERPTS
    CITES BACKGROUND & METHODS

    An anatomy for neural search engines

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Parrot: A Python-based Interactive Platform for Information Retrieval Research

    VIEW 4 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Teach Machine How to Read: Reading Behavior Inspired Relevance Estimation

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 4 Highly Influenced Citations

    • Averaged 18 Citations per year from 2017 through 2019

    • 193% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 10 REFERENCES

    From RankNet to LambdaRank to LambdaMART: An Overview

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Optimizing search engines using clickthrough data

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    An Efficient Boosting Algorithm for Combining Preferences

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL