• DOI:10.18653/v1/P18-1190
Corpus ID: 13692090

NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing

@article{Shen2018NASHTE,
  title={NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing},
  author={Dinghan Shen and Qinliang Su and Paidamoyo Chapfuwa and W. Wang and Guoyin Wang and L. Carin and Ricardo Henao},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.05361}
}

Dinghan Shen, Qinliang Su, +4 authors Ricardo Henao

Published 2018

Computer Science

ArXiv

Semantic hashing has become a powerful paradigm for fast similarity search in many information retrieval systems. While fairly successful, previous techniques generally require two-stage training, and the binary constraints are handled ad-hoc. In this paper, we present an end-to-end Neural Architecture for Semantic Hashing (NASH), where the binary hashing codes are treated as Bernoulli latent variables. A neural variational inference framework is proposed for training, where gradients are… CONTINUE READING

View on ACL

people.ee.duke.edu

Save to Library

Create Alert

Cite

Launch Research Feed