@inproceedings{shen-etal-2018-nash,
title = "{NASH}: Toward End-to-End Neural Architecture for Generative Semantic Hashing",
author = "Shen, Dinghan and
Su, Qinliang and
Chapfuwa, Paidamoyo and
Wang, Wenlin and
Wang, Guoyin and
Henao, Ricardo and
Carin, Lawrence",
editor = "Gurevych, Iryna and
Miyao, Yusuke",
booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P18-1190",
doi = "10.18653/v1/P18-1190",
pages = "2041--2050",
abstract = "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 \textit{ad-hoc}. In this paper, we present an \textit{end-to-end} Neural Architecture for Semantic Hashing (NASH), where the binary hashing codes are treated as \textit{Bernoulli} latent variables. A neural variational inference framework is proposed for training, where gradients are directly backpropagated through the discrete latent variable to optimize the hash function. We also draw the connections between proposed method and \textit{rate-distortion theory}, which provides a theoretical foundation for the effectiveness of our framework. Experimental results on three public datasets demonstrate that our method significantly outperforms several state-of-the-art models on both \textit{unsupervised} and \textit{supervised} scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2018-nash">
<titleInfo>
<title>NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dinghan</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qinliang</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paidamoyo</namePart>
<namePart type="family">Chapfuwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenlin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoyin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ricardo</namePart>
<namePart type="family">Henao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="family">Carin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iryna</namePart>
<namePart type="family">Gurevych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Miyao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>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 directly backpropagated through the discrete latent variable to optimize the hash function. We also draw the connections between proposed method and rate-distortion theory, which provides a theoretical foundation for the effectiveness of our framework. Experimental results on three public datasets demonstrate that our method significantly outperforms several state-of-the-art models on both unsupervised and supervised scenarios.</abstract>
<identifier type="citekey">shen-etal-2018-nash</identifier>
<identifier type="doi">10.18653/v1/P18-1190</identifier>
<location>
<url>https://aclanthology.org/P18-1190</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>2041</start>
<end>2050</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing
%A Shen, Dinghan
%A Su, Qinliang
%A Chapfuwa, Paidamoyo
%A Wang, Wenlin
%A Wang, Guoyin
%A Henao, Ricardo
%A Carin, Lawrence
%Y Gurevych, Iryna
%Y Miyao, Yusuke
%S Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F shen-etal-2018-nash
%X 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 directly backpropagated through the discrete latent variable to optimize the hash function. We also draw the connections between proposed method and rate-distortion theory, which provides a theoretical foundation for the effectiveness of our framework. Experimental results on three public datasets demonstrate that our method significantly outperforms several state-of-the-art models on both unsupervised and supervised scenarios.
%R 10.18653/v1/P18-1190
%U https://aclanthology.org/P18-1190
%U https://doi.org/10.18653/v1/P18-1190
%P 2041-2050
Markdown (Informal)
[NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing](https://aclanthology.org/P18-1190) (Shen et al., ACL 2018)
ACL
- Dinghan Shen, Qinliang Su, Paidamoyo Chapfuwa, Wenlin Wang, Guoyin Wang, Ricardo Henao, and Lawrence Carin. 2018. NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2041–2050, Melbourne, Australia. Association for Computational Linguistics.