<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="galke-scherp-2022-bag">
    <titleInfo>
        <title>Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Lukas</namePart>
        <namePart type="family">Galke</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ansgar</namePart>
        <namePart type="family">Scherp</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Graph neural networks have triggered a resurgence of graph-based text classification methods, defining today’s state of the art. We show that a wide multi-layer perceptron (MLP) using a Bag-of-Words (BoW) outperforms the recent graph-based models TextGCN and HeteGCN in an inductive text classification setting and is comparable with HyperGAT. Moreover, we fine-tune a sequence-based BERT and a lightweight DistilBERT model, which both outperform all state-of-the-art models. These results question the importance of synthetic graphs used in modern text classifiers. In terms of efficiency, DistilBERT is still twice as large as our BoW-based wide MLP, while graph-based models like TextGCN require setting up an \mathcalO(N²) graph, where N is the vocabulary plus corpus size. Finally, since Transformers need to compute \mathcalO(L²) attention weights with sequence length L, the MLP models show higher training and inference speeds on datasets with long sequences.</abstract>
    <identifier type="citekey">galke-scherp-2022-bag</identifier>
    <identifier type="doi">10.18653/v1/2022.acl-long.279</identifier>
    <location>
        <url>https://aclanthology.org/2022.acl-long.279</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>4038</start>
            <end>4051</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP
%A Galke, Lukas
%A Scherp, Ansgar
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F galke-scherp-2022-bag
%X Graph neural networks have triggered a resurgence of graph-based text classification methods, defining today’s state of the art. We show that a wide multi-layer perceptron (MLP) using a Bag-of-Words (BoW) outperforms the recent graph-based models TextGCN and HeteGCN in an inductive text classification setting and is comparable with HyperGAT. Moreover, we fine-tune a sequence-based BERT and a lightweight DistilBERT model, which both outperform all state-of-the-art models. These results question the importance of synthetic graphs used in modern text classifiers. In terms of efficiency, DistilBERT is still twice as large as our BoW-based wide MLP, while graph-based models like TextGCN require setting up an \mathcalO(N²) graph, where N is the vocabulary plus corpus size. Finally, since Transformers need to compute \mathcalO(L²) attention weights with sequence length L, the MLP models show higher training and inference speeds on datasets with long sequences.
%R 10.18653/v1/2022.acl-long.279
%U https://aclanthology.org/2022.acl-long.279
%U https://doi.org/10.18653/v1/2022.acl-long.279
%P 4038-4051

Markdown (Informal)

[Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP](https://aclanthology.org/2022.acl-long.279) (Galke & Scherp, ACL 2022)

• Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP (Galke & Scherp, ACL 2022)

ACL

• Lukas Galke and Ansgar Scherp. 2022. Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4038–4051, Dublin, Ireland. Association for Computational Linguistics.