@inproceedings{card-etal-2018-neural,
title = "Neural Models for Documents with Metadata",
author = "Card, Dallas and
Tan, Chenhao and
Smith, Noah A.",
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/P18-1189",
doi = "10.18653/v1/P18-1189",
pages = "2031--2040",
abstract = "Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been developed for particular applications, few are widely used in practice, as customization typically requires derivation of a custom inference algorithm. In this paper, we build on recent advances in variational inference methods and propose a general neural framework, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration of alternative models. Our approach achieves strong performance, with a manageable tradeoff between perplexity, coherence, and sparsity. Finally, we demonstrate the potential of our framework through an exploration of a corpus of articles about US immigration.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="card-etal-2018-neural">
<titleInfo>
<title>Neural Models for Documents with Metadata</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dallas</namePart>
<namePart type="family">Card</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhao</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</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>Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been developed for particular applications, few are widely used in practice, as customization typically requires derivation of a custom inference algorithm. In this paper, we build on recent advances in variational inference methods and propose a general neural framework, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration of alternative models. Our approach achieves strong performance, with a manageable tradeoff between perplexity, coherence, and sparsity. Finally, we demonstrate the potential of our framework through an exploration of a corpus of articles about US immigration.</abstract>
<identifier type="citekey">card-etal-2018-neural</identifier>
<identifier type="doi">10.18653/v1/P18-1189</identifier>
<location>
<url>https://aclanthology.org/P18-1189</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>2031</start>
<end>2040</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Models for Documents with Metadata
%A Card, Dallas
%A Tan, Chenhao
%A Smith, Noah A.
%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 card-etal-2018-neural
%X Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been developed for particular applications, few are widely used in practice, as customization typically requires derivation of a custom inference algorithm. In this paper, we build on recent advances in variational inference methods and propose a general neural framework, based on topic models, to enable flexible incorporation of metadata and allow for rapid exploration of alternative models. Our approach achieves strong performance, with a manageable tradeoff between perplexity, coherence, and sparsity. Finally, we demonstrate the potential of our framework through an exploration of a corpus of articles about US immigration.
%R 10.18653/v1/P18-1189
%U https://aclanthology.org/P18-1189
%U https://doi.org/10.18653/v1/P18-1189
%P 2031-2040
Markdown (Informal)
[Neural Models for Documents with Metadata](https://aclanthology.org/P18-1189) (Card et al., ACL 2018)
ACL
- Dallas Card, Chenhao Tan, and Noah A. Smith. 2018. Neural Models for Documents with Metadata. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2031–2040, Melbourne, Australia. Association for Computational Linguistics.