<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="opitz-etal-2023-smaragd">
    <titleInfo>
        <title>SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Juri</namePart>
        <namePart type="family">Opitz</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Meier</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anette</namePart>
        <namePart type="family">Frank</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-06</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Computational Semantics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maxime</namePart>
            <namePart type="family">Amblard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ellen</namePart>
            <namePart type="family">Breitholtz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Nancy, France</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>The similarity of graph structures, such as Meaning Representations (MRs), is often assessed via structural matching algorithms, such as Smatch (Cai &amp; Knight 2013). However, Smatch involves a combinatorial problem that suffers from NP-completeness, making large-scale applications, e.g., graph clustering or search, infeasible. To alleviate this issue, we learn SMARAGD: Semantic Match for Accurate and Rapid Approximate Graph Distance. We show the potential of neural networks to approximate Smatch scores, i) in linear time using a machine translation framework to predict alignments, or ii) in constant time using a Siamese CNN to directly predict Smatch scores. We show that the approximation error can be substantially reduced through data augmentation and graph anonymization.</abstract>
    <identifier type="citekey">opitz-etal-2023-smaragd</identifier>
    <location>
        <url>https://aclanthology.org/2023.iwcs-1.28</url>
    </location>
    <part>
        <date>2023-06</date>
        <extent unit="page">
            <start>267</start>
            <end>274</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance
%A Opitz, Juri
%A Meier, Philipp
%A Frank, Anette
%Y Amblard, Maxime
%Y Breitholtz, Ellen
%S Proceedings of the 15th International Conference on Computational Semantics
%D 2023
%8 June
%I Association for Computational Linguistics
%C Nancy, France
%F opitz-etal-2023-smaragd
%X The similarity of graph structures, such as Meaning Representations (MRs), is often assessed via structural matching algorithms, such as Smatch (Cai & Knight 2013). However, Smatch involves a combinatorial problem that suffers from NP-completeness, making large-scale applications, e.g., graph clustering or search, infeasible. To alleviate this issue, we learn SMARAGD: Semantic Match for Accurate and Rapid Approximate Graph Distance. We show the potential of neural networks to approximate Smatch scores, i) in linear time using a machine translation framework to predict alignments, or ii) in constant time using a Siamese CNN to directly predict Smatch scores. We show that the approximation error can be substantially reduced through data augmentation and graph anonymization.
%U https://aclanthology.org/2023.iwcs-1.28
%P 267-274

Markdown (Informal)

[SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance](https://aclanthology.org/2023.iwcs-1.28) (Opitz et al., IWCS 2023)

• SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance (Opitz et al., IWCS 2023)

ACL

• Juri Opitz, Philipp Meier, and Anette Frank. 2023. SMARAGD: Learning SMatch for Accurate and Rapid Approximate Graph Distance. In Proceedings of the 15th International Conference on Computational Semantics, pages 267–274, Nancy, France. Association for Computational Linguistics.