@inproceedings{guo-2017-deep,
title = "A Deep Network with Visual Text Composition Behavior",
author = "Guo, Hongyu",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-2059",
doi = "10.18653/v1/P17-2059",
pages = "372--377",
abstract = "While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-2017-deep">
<titleInfo>
<title>A Deep Network with Visual Text Composition Behavior</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</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>While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.</abstract>
<identifier type="citekey">guo-2017-deep</identifier>
<identifier type="doi">10.18653/v1/P17-2059</identifier>
<location>
<url>https://aclanthology.org/P17-2059</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>372</start>
<end>377</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Deep Network with Visual Text Composition Behavior
%A Guo, Hongyu
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F guo-2017-deep
%X While natural languages are compositional, how state-of-the-art neural models achieve compositionality is still unclear. We propose a deep network, which not only achieves competitive accuracy for text classification, but also exhibits compositional behavior. That is, while creating hierarchical representations of a piece of text, such as a sentence, the lower layers of the network distribute their layer-specific attention weights to individual words. In contrast, the higher layers compose meaningful phrases and clauses, whose lengths increase as the networks get deeper until fully composing the sentence.
%R 10.18653/v1/P17-2059
%U https://aclanthology.org/P17-2059
%U https://doi.org/10.18653/v1/P17-2059
%P 372-377
Markdown (Informal)
[A Deep Network with Visual Text Composition Behavior](https://aclanthology.org/P17-2059) (Guo, ACL 2017)
ACL
- Hongyu Guo. 2017. A Deep Network with Visual Text Composition Behavior. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 372–377, Vancouver, Canada. Association for Computational Linguistics.