End-to-End Neural Ad-hoc Ranking with Kernel Pooling

@article{Xiong2017EndtoEndNA,
  title={End-to-End Neural Ad-hoc Ranking with Kernel Pooling},
  author={Chenyan Xiong and Zhuyun Dai and James P. Callan and Zhiyuan Liu and Russell Power},
  journal={ArXiv},
  year={2017},
  volume={abs/1706.06613}
}
This paper proposes K-NRM, a kernel based neural model for document ranking. Given a query and a set of documents, K-NRM uses a translation matrix that models word-level similarities via word embeddings, a new kernel-pooling technique that uses kernels to extract multi-level soft match features, and a learning-to-rank layer that combines those features into the final ranking score. The whole model is trained end-to-end. The ranking layer learns desired feature patterns from the pairwise ranking… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 124 CITATIONS

End-to-end Neural Information Retrieval

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Neural Document Expansion with User Feedback

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND

On the Effect of Low-Frequency Terms on Neural-IR Models

VIEW 10 EXCERPTS
CITES RESULTS & METHODS
HIGHLY INFLUENCED

A Deep Relevance Model for Zero-Shot Document Filtering

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

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

VIEW 10 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Deep Look into Neural Ranking Models for Information Retrieval

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Hierarchical Attention Retrieval Model for Healthcare Question Answering

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 35 Highly Influenced Citations

  • Averaged 38 Citations per year from 2017 through 2019

  • 49% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-6 OF 6 REFERENCES

A Deep Relevance Matching Model for Ad-hoc Retrieval

VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Time-Aware Click Model

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Click Models for Web Search

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL