CEDR: Contextualized Embeddings for Document Ranking

@article{MacAvaney2019CEDRCE,
  title={CEDR: Contextualized Embeddings for Document Ranking},
  author={Sean MacAvaney and Andrew Yates and Arman Cohan and Nazli Goharian},
  journal={Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year={2019}
}
  • Sean MacAvaney, Andrew Yates, +1 author Nazli Goharian
  • Published in SIGIR'19 2019
  • Computer Science
  • Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
  • Although considerable attention has been given to neural ranking architectures recently, far less attention has been paid to the term representations that are used as input to these models. [...] Key Method Furthermore, we propose a joint approach that incorporates BERT's classification vector into existing neural models and show that it outperforms state-of-the-art ad-hoc ranking baselines. We call this joint approach CEDR (Contextualized Embeddings for Document Ranking). We also address practical challenges…Expand Abstract

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 37 CITATIONS

    Efficient Document Re-Ranking for Transformers by Precomputing Term Representations

    VIEW 13 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Selective Weak Supervision for Neural Information Retrieval

    VIEW 5 EXCERPTS
    CITES METHODS & RESULTS
    HIGHLY INFLUENCED

    Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Capreolus: A Toolkit for End-to-End Neural Ad Hoc Retrieval

    VIEW 2 EXCERPTS
    CITES RESULTS

    References

    Publications referenced by this paper.
    SHOWING 1-4 OF 4 REFERENCES

    Adam: A Method for Stochastic Optimization

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    A Markov random field model for term dependencies

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    Robust Track Experiments using PIRCS

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL