@inproceedings{bolucu-can-2023-sentence,
title = "Which Sentence Representation is More Informative: An Analysis on Text Classification",
author = {B{\"o}l{\"u}c{\"u}, Necva and
Can, Burcu},
editor = "Rambow, Owen and
Lareau, Fran{\c{c}}ois",
booktitle = "Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023)",
month = mar,
year = "2023",
address = "Washington, D.C.",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.depling-1.2",
pages = "9--21",
abstract = "Text classification is a popular and well-studied problem in Natural Language Processing. Most previous work on text classification has focused on deep neural networks such as LSTMs and CNNs. However, text classification studies using syntactic and semantic information are very limited in the literature. In this study, we propose a model using Graph Attention Network (GAT) that incorporates semantic and syntactic information as input for the text classification task. The semantic representations of UCCA and AMR are used as semantic information and the dependency tree is used as syntactic information. Extensive experimental results and in-depth analysis show that UCCA-GAT model, which is a semantic-aware model outperforms the AMR-GAT and DEP-GAT, which are semantic and syntax-aware models respectively. We also provide a comprehensive analysis of the proposed model to understand the limitations of the representations for the problem.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bolucu-can-2023-sentence">
<titleInfo>
<title>Which Sentence Representation is More Informative: An Analysis on Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Necva</namePart>
<namePart type="family">Bölücü</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">François</namePart>
<namePart type="family">Lareau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Washington, D.C.</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text classification is a popular and well-studied problem in Natural Language Processing. Most previous work on text classification has focused on deep neural networks such as LSTMs and CNNs. However, text classification studies using syntactic and semantic information are very limited in the literature. In this study, we propose a model using Graph Attention Network (GAT) that incorporates semantic and syntactic information as input for the text classification task. The semantic representations of UCCA and AMR are used as semantic information and the dependency tree is used as syntactic information. Extensive experimental results and in-depth analysis show that UCCA-GAT model, which is a semantic-aware model outperforms the AMR-GAT and DEP-GAT, which are semantic and syntax-aware models respectively. We also provide a comprehensive analysis of the proposed model to understand the limitations of the representations for the problem.</abstract>
<identifier type="citekey">bolucu-can-2023-sentence</identifier>
<location>
<url>https://aclanthology.org/2023.depling-1.2</url>
</location>
<part>
<date>2023-03</date>
<extent unit="page">
<start>9</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Which Sentence Representation is More Informative: An Analysis on Text Classification
%A Bölücü, Necva
%A Can, Burcu
%Y Rambow, Owen
%Y Lareau, François
%S Proceedings of the Seventh International Conference on Dependency Linguistics (Depling, GURT/SyntaxFest 2023)
%D 2023
%8 March
%I Association for Computational Linguistics
%C Washington, D.C.
%F bolucu-can-2023-sentence
%X Text classification is a popular and well-studied problem in Natural Language Processing. Most previous work on text classification has focused on deep neural networks such as LSTMs and CNNs. However, text classification studies using syntactic and semantic information are very limited in the literature. In this study, we propose a model using Graph Attention Network (GAT) that incorporates semantic and syntactic information as input for the text classification task. The semantic representations of UCCA and AMR are used as semantic information and the dependency tree is used as syntactic information. Extensive experimental results and in-depth analysis show that UCCA-GAT model, which is a semantic-aware model outperforms the AMR-GAT and DEP-GAT, which are semantic and syntax-aware models respectively. We also provide a comprehensive analysis of the proposed model to understand the limitations of the representations for the problem.
%U https://aclanthology.org/2023.depling-1.2
%P 9-21
Markdown (Informal)
[Which Sentence Representation is More Informative: An Analysis on Text Classification](https://aclanthology.org/2023.depling-1.2) (Bölücü & Can, DepLing-SyntaxFest 2023)
ACL