Efficient and Effective Tail Latency Minimization in Multi-Stage Retrieval Systems

@article{Mackenzie2017EfficientAE,
  title={Efficient and Effective Tail Latency Minimization in Multi-Stage Retrieval Systems},
  author={Joel Mackenzie and J. Shane Culpepper and Roi Blanco and Matt Crane and Charles L. A. Clarke and Jimmy J. Lin},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.03970}
}
  • Joel Mackenzie, J. Shane Culpepper, +3 authors Jimmy J. Lin
  • Published 2017
  • Computer Science
  • ArXiv
  • Scalable web search systems typically employ multi-stage retrieval architectures, where an initial stage generates a set of candidate documents that are then pruned and re-ranked. Since subsequent stages typically exploit a multitude of features of varying costs using machine-learned models, reducing the number of documents that are considered at each stage improves latency. In this work, we propose and validate a uni€ed framework that can be used to predict a wide range of performance… CONTINUE READING

    Citations

    Publications citing this paper.

    Managing Tail Latencies in Large Scale IR Systems

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 62 REFERENCES

    Faster top-k document retrieval using block-max indexes

    VIEW 2 EXCERPTS