@inproceedings{grzegorczyk-kurdziel-2017-binary,
title = "Binary Paragraph Vectors",
author = "Grzegorczyk, Karol and
Kurdziel, Marcin",
editor = "Blunsom, Phil and
Bordes, Antoine and
Cho, Kyunghyun and
Cohen, Shay and
Dyer, Chris and
Grefenstette, Edward and
Hermann, Karl Moritz and
Rimell, Laura and
Weston, Jason and
Yih, Scott",
booktitle = "Proceedings of the 2nd Workshop on Representation Learning for {NLP}",
month = aug,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-2615",
doi = "10.18653/v1/W17-2615",
pages = "121--130",
abstract = "Recently Le {\&} Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-of-the-art distributed representations of documents. Inspired by this work, we present Binary Paragraph Vector models: simple neural networks that learn short binary codes for fast information retrieval. We show that binary paragraph vectors outperform autoencoder-based binary codes, despite using fewer bits. We also evaluate their precision in transfer learning settings, where binary codes are inferred for documents unrelated to the training corpus. Results from these experiments indicate that binary paragraph vectors can capture semantics relevant for various domain-specific documents. Finally, we present a model that simultaneously learns short binary codes and longer, real-valued representations. This model can be used to rapidly retrieve a short list of highly relevant documents from a large document collection.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grzegorczyk-kurdziel-2017-binary">
<titleInfo>
<title>Binary Paragraph Vectors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karol</namePart>
<namePart type="family">Grzegorczyk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcin</namePart>
<namePart type="family">Kurdziel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bordes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyunghyun</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shay</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Dyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edward</namePart>
<namePart type="family">Grefenstette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="given">Moritz</namePart>
<namePart type="family">Hermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Rimell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Weston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently Le & Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-of-the-art distributed representations of documents. Inspired by this work, we present Binary Paragraph Vector models: simple neural networks that learn short binary codes for fast information retrieval. We show that binary paragraph vectors outperform autoencoder-based binary codes, despite using fewer bits. We also evaluate their precision in transfer learning settings, where binary codes are inferred for documents unrelated to the training corpus. Results from these experiments indicate that binary paragraph vectors can capture semantics relevant for various domain-specific documents. Finally, we present a model that simultaneously learns short binary codes and longer, real-valued representations. This model can be used to rapidly retrieve a short list of highly relevant documents from a large document collection.</abstract>
<identifier type="citekey">grzegorczyk-kurdziel-2017-binary</identifier>
<identifier type="doi">10.18653/v1/W17-2615</identifier>
<location>
<url>https://aclanthology.org/W17-2615</url>
</location>
<part>
<date>2017-08</date>
<extent unit="page">
<start>121</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Binary Paragraph Vectors
%A Grzegorczyk, Karol
%A Kurdziel, Marcin
%Y Blunsom, Phil
%Y Bordes, Antoine
%Y Cho, Kyunghyun
%Y Cohen, Shay
%Y Dyer, Chris
%Y Grefenstette, Edward
%Y Hermann, Karl Moritz
%Y Rimell, Laura
%Y Weston, Jason
%Y Yih, Scott
%S Proceedings of the 2nd Workshop on Representation Learning for NLP
%D 2017
%8 August
%I Association for Computational Linguistics
%C Vancouver, Canada
%F grzegorczyk-kurdziel-2017-binary
%X Recently Le & Mikolov described two log-linear models, called Paragraph Vector, that can be used to learn state-of-the-art distributed representations of documents. Inspired by this work, we present Binary Paragraph Vector models: simple neural networks that learn short binary codes for fast information retrieval. We show that binary paragraph vectors outperform autoencoder-based binary codes, despite using fewer bits. We also evaluate their precision in transfer learning settings, where binary codes are inferred for documents unrelated to the training corpus. Results from these experiments indicate that binary paragraph vectors can capture semantics relevant for various domain-specific documents. Finally, we present a model that simultaneously learns short binary codes and longer, real-valued representations. This model can be used to rapidly retrieve a short list of highly relevant documents from a large document collection.
%R 10.18653/v1/W17-2615
%U https://aclanthology.org/W17-2615
%U https://doi.org/10.18653/v1/W17-2615
%P 121-130
Markdown (Informal)
[Binary Paragraph Vectors](https://aclanthology.org/W17-2615) (Grzegorczyk & Kurdziel, RepL4NLP 2017)
ACL
- Karol Grzegorczyk and Marcin Kurdziel. 2017. Binary Paragraph Vectors. In Proceedings of the 2nd Workshop on Representation Learning for NLP, pages 121–130, Vancouver, Canada. Association for Computational Linguistics.